Header logo is am


2016


no image
Predictive and Self Triggering for Event-based State Estimation

Trimpe, S.

In Proceedings of the 55th IEEE Conference on Decision and Control (CDC), pages: 3098-3105, Las Vegas, NV, USA, December 2016 (inproceedings)

arXiv PDF DOI Project Page [BibTex]

2016

arXiv PDF DOI Project Page [BibTex]


no image
Using Probabilistic Movement Primitives for Striking Movements

Gomez-Gonzalez, S., Neumann, G., Schölkopf, B., Peters, J.

16th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pages: 502-508, November 2016 (conference)

link (url) DOI Project Page [BibTex]

link (url) DOI Project Page [BibTex]


Thumb xl screen shot 2019 01 07 at 11.54.16
Jointly Learning Trajectory Generation and Hitting Point Prediction in Robot Table Tennis

Huang, Y., Büchler, D., Koc, O., Schölkopf, B., Peters, J.

16th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pages: 650-655, November 2016 (conference)

final link (url) DOI Project Page [BibTex]

final link (url) DOI Project Page [BibTex]


no image
The Role of Measurement Uncertainty in Optimal Control for Contact Interactions
Workshop on the Algorithmic Foundations of Robotics, pages: 22, November 2016 (conference)

Abstract
Stochastic Optimal Control (SOC) typically considers noise only in the process model, i.e. unknown disturbances. However, in many robotic applications that involve interaction with the environment, such as locomotion and manipulation, uncertainty also comes from lack of pre- cise knowledge of the world, which is not an actual disturbance. We de- velop a computationally efficient SOC algorithm, based on risk-sensitive control, that takes into account uncertainty in the measurements. We include the dynamics of an observer in such a way that the control law explicitly depends on the current measurement uncertainty. We show that high measurement uncertainty leads to low impedance behaviors, a result in contrast with the effects of process noise variance that creates stiff behaviors. Simulation results on a simple 2D manipulator show that our controller can create better interaction with the environment under uncertain contact locations than traditional SOC approaches.

arXiv [BibTex]

arXiv [BibTex]


Thumb xl img
Learning Where to Search Using Visual Attention

Kloss, A., Kappler, D., Lensch, H. P. A., Butz, M. V., Schaal, S., Bohg, J.

Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, IEEE, IROS, October 2016 (conference)

Abstract
One of the central tasks for a household robot is searching for specific objects. It does not only require localizing the target object but also identifying promising search locations in the scene if the target is not immediately visible. As computation time and hardware resources are usually limited in robotics, it is desirable to avoid expensive visual processing steps that are exhaustively applied over the entire image. The human visual system can quickly select those image locations that have to be processed in detail for a given task. This allows us to cope with huge amounts of information and to efficiently deploy the limited capacities of our visual system. In this paper, we therefore propose to use human fixation data to train a top-down saliency model that predicts relevant image locations when searching for specific objects. We show that the learned model can successfully prune bounding box proposals without rejecting the ground truth object locations. In this aspect, the proposed model outperforms a model that is trained only on the ground truth segmentations of the target object instead of fixation data.

Project Page [BibTex]

PDF Project Page [BibTex]


Thumb xl oxfordlight
Parameter Learning for Improving Binary Descriptor Matching

Sankaran, B., Ramalingam, S., Taguchi, Y.

In International Conference on Intelligent Robots and Systems (IROS) 2016, IEEE/RSJ International Conference on Intelligent Robots and Systems, October 2016 (inproceedings)

Abstract
Binary descriptors allow fast detection and matching algorithms in computer vision problems. Though binary descriptors can be computed at almost two orders of magnitude faster than traditional gradient based descriptors, they suffer from poor matching accuracy in challenging conditions. In this paper we propose three improvements for binary descriptors in their computation and matching that enhance their performance in comparison to traditional binary and non-binary descriptors without compromising their speed. This is achieved by learning some weights and threshold parameters that allow customized matching under some variations such as lighting and viewpoint. Our suggested improvements can be easily applied to any binary descriptor. We demonstrate our approach on the ORB (Oriented FAST and Rotated BRIEF) descriptor and compare its performance with the traditional ORB and SIFT descriptors on a wide variety of datasets. In all instances, our enhancements outperform standard ORB and is comparable to SIFT.

[BibTex]

[BibTex]


no image
A New Trajectory Generation Framework in Robotic Table Tennis

Koc, O., Maeda, G., Peters, J.

Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), pages: 3750-3756, October 2016 (conference)

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl gadde
Superpixel Convolutional Networks using Bilateral Inceptions

Gadde, R., Jampani, V., Kiefel, M., Kappler, D., Gehler, P.

In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, Springer, 14th European Conference on Computer Vision, October 2016 (inproceedings)

Abstract
In this paper we propose a CNN architecture for semantic image segmentation. We introduce a new “bilateral inception” module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image. The feature spaces for bilateral filtering and other parameters of the module are learned end-to-end using standard backpropagation techniques. The bilateral inception module addresses two issues that arise with general CNN segmentation architectures. First, this module propagates information between (super) pixels while respecting image edges, thus using the structured information of the problem for improved results. Second, the layer recovers a full resolution segmentation result from the lower resolution solution of a CNN. In the experiments, we modify several existing CNN architectures by inserting our inception modules between the last CNN (1 × 1 convolution) layers. Empirical results on three different datasets show reliable improvements not only in comparison to the baseline networks, but also in comparison to several dense-pixel prediction techniques such as CRFs, while being competitive in time.

pdf supplementary poster Project Page Project Page [BibTex]

pdf supplementary poster Project Page Project Page [BibTex]


Thumb xl thumb
Barrista - Caffe Well-Served

Lassner, C., Kappler, D., Kiefel, M., Gehler, P.

In ACM Multimedia Open Source Software Competition, ACM OSSC16, October 2016 (inproceedings)

Abstract
The caffe framework is one of the leading deep learning toolboxes in the machine learning and computer vision community. While it offers efficiency and configurability, it falls short of a full interface to Python. With increasingly involved procedures for training deep networks and reaching depths of hundreds of layers, creating configuration files and keeping them consistent becomes an error prone process. We introduce the barrista framework, offering full, pythonic control over caffe. It separates responsibilities and offers code to solve frequently occurring tasks for pre-processing, training and model inspection. It is compatible to all caffe versions since mid 2015 and can import and export .prototxt files. Examples are included, e.g., a deep residual network implemented in only 172 lines (for arbitrary depths), comparing to 2320 lines in the official implementation for the equivalent model.

pdf link (url) DOI Project Page [BibTex]

pdf link (url) DOI Project Page [BibTex]


Thumb xl screen shot 2015 12 04 at 15.11.43
Robust Gaussian Filtering using a Pseudo Measurement

Wüthrich, M., Garcia Cifuentes, C., Trimpe, S., Meier, F., Bohg, J., Issac, J., Schaal, S.

In Proceedings of the American Control Conference (ACC), Boston, MA, USA, July 2016 (inproceedings)

Abstract
Most widely-used state estimation algorithms, such as the Extended Kalman Filter and the Unscented Kalman Filter, belong to the family of Gaussian Filters (GF). Unfortunately, GFs fail if the measurement process is modelled by a fat-tailed distribution. This is a severe limitation, because thin-tailed measurement models, such as the analytically-convenient and therefore widely-used Gaussian distribution, are sensitive to outliers. In this paper, we show that mapping the measurements into a specific feature space enables any existing GF algorithm to work with fat-tailed measurement models. We find a feature function which is optimal under certain conditions. Simulation results show that the proposed method allows for robust filtering in both linear and nonlinear systems with measurements contaminated by fat-tailed noise.

Web link (url) DOI Project Page [BibTex]

Web link (url) DOI Project Page [BibTex]


Thumb xl pic for website small
Robot Arm Pose Estimation by Pixel-wise Regression of Joint Angles

Widmaier, F., Kappler, D., Schaal, S., Bohg, J.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2016, IEEE, IEEE International Conference on Robotics and Automation, May 2016 (inproceedings)

Abstract
To achieve accurate vision-based control with a robotic arm, a good hand-eye coordination is required. However, knowing the current configuration of the arm can be very difficult due to noisy readings from joint encoders or an inaccurate hand-eye calibration. We propose an approach for robot arm pose estimation that uses depth images of the arm as input to directly estimate angular joint positions. This is a frame-by-frame method which does not rely on good initialisation of the solution from the previous frames or knowledge from the joint encoders. For estimation, we employ a random regression forest which is trained on synthetically generated data. We compare different training objectives of the forest and also analyse the influence of prior segmentation of the arms on accuracy. We show that this approach improves previous work both in terms of computational complexity and accuracy. Despite being trained on synthetic data only, we demonstrate that the estimation also works on real depth images.

pdf DOI Project Page [BibTex]

pdf DOI Project Page [BibTex]


Thumb xl ranking top 1
Optimizing for what matters: the Top Grasp Hypothesis

Kappler, D., Schaal, S., Bohg, J.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2016, IEEE, IEEE International Conference on Robotics and Automation, May 2016 (inproceedings)

Abstract
In this paper, we consider the problem of robotic grasping of objects when only partial and noisy sensor data of the environment is available. We are specifically interested in the problem of reliably selecting the best hypothesis from a whole set. This is commonly the case when trying to grasp an object for which we can only observe a partial point cloud from one viewpoint through noisy sensors. There will be many possible ways to successfully grasp this object, and even more which will fail. We propose a supervised learning method that is trained with a ranking loss. This explicitly encourages that the top-ranked training grasp in a hypothesis set is also positively labeled. We show how we adapt the standard ranking loss to work with data that has binary labels and explain the benefits of this formulation. Additionally, we show how we can efficiently optimize this loss with stochastic gradient descent. In quantitative experiments, we show that we can outperform previous models by a large margin.

pdf DOI Project Page [BibTex]

pdf DOI Project Page [BibTex]


Thumb xl retrieved templates 3
Exemplar-based Prediction of Object Properties from Local Shape Similarity

Bohg, J., Kappler, D., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2016, IEEE, IEEE International Conference on Robotics and Automation, May 2016 (inproceedings)

Abstract
We propose a novel method that enables a robot to identify a graspable object part of an unknown object given only noisy and partial information that is obtained from an RGB-D camera. Our method combines the benefits of local with the advantages of global methods. It learns a classifier that takes a local shape representation as input and outputs the probability that a grasp applied at this location will be successful. Given a query data point that is classified in this way, we can retrieve all the locally similar training data points and use them to predict latent global object shape. This information may help to further prune positively labeled grasp hypotheses based on, e.g. relation to the predicted average global shape or suitability for a specific task. This prediction can also guide scene exploration to prune object shape hypotheses. To learn the function that maps local shape to grasp stability we use a Random Forest Classifier. We show that our method reaches the same classification performance as the current state-of-the-art on this dataset which uses a Convolutional Neural Network. Additionally, we exploit the natural ability of the Random Forest to cluster similar data. For a positively predicted query data point, we retrieve all the locally similar training data points that are associated with the same leaf nodes of the Random Forest. The main insight from this work is that local object shape that affords a grasp is also a good predictor of global object shape. We empirically support this claim with quantitative experiments. Additionally, we demonstrate the predictive capability of the method on some real data examples.

pdf DOI Project Page [BibTex]

pdf DOI Project Page [BibTex]


Thumb xl screen shot 2016 01 19 at 14.48.37
Automatic LQR Tuning Based on Gaussian Process Global Optimization

Marco, A., Hennig, P., Bohg, J., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 270-277, IEEE, IEEE International Conference on Robotics and Automation, May 2016 (inproceedings)

Abstract
This paper proposes an automatic controller tuning framework based on linear optimal control combined with Bayesian optimization. With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data. The underlying Bayesian optimization algorithm is Entropy Search, which represents the latent objective as a Gaussian process and constructs an explicit belief over the location of the objective minimum. This is used to maximize the information gain from each experimental evaluation. Thus, this framework shall yield improved controllers with fewer evaluations compared to alternative approaches. A seven-degree- of-freedom robot arm balancing an inverted pole is used as the experimental demonstrator. Results of a two- and four- dimensional tuning problems highlight the method’s potential for automatic controller tuning on robotic platforms.

Video PDF DOI Project Page [BibTex]

Video PDF DOI Project Page [BibTex]


Thumb xl screen shot 2016 01 19 at 14.56.20
Depth-based Object Tracking Using a Robust Gaussian Filter

Issac, J., Wüthrich, M., Garcia Cifuentes, C., Bohg, J., Trimpe, S., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2016, IEEE, IEEE International Conference on Robotics and Automation, May 2016 (inproceedings)

Abstract
We consider the problem of model-based 3D- tracking of objects given dense depth images as input. Two difficulties preclude the application of a standard Gaussian filter to this problem. First of all, depth sensors are characterized by fat-tailed measurement noise. To address this issue, we show how a recently published robustification method for Gaussian filters can be applied to the problem at hand. Thereby, we avoid using heuristic outlier detection methods that simply reject measurements if they do not match the model. Secondly, the computational cost of the standard Gaussian filter is prohibitive due to the high-dimensional measurement, i.e. the depth image. To address this problem, we propose an approximation to reduce the computational complexity of the filter. In quantitative experiments on real data we show how our method clearly outperforms the standard Gaussian filter. Furthermore, we compare its performance to a particle-filter-based tracking method, and observe comparable computational efficiency and improved accuracy and smoothness of the estimates.

Video Bayesian Object Tracking Library Bayesian Filtering Framework Object Tracking Dataset link (url) DOI Project Page [BibTex]

Video Bayesian Object Tracking Library Bayesian Filtering Framework Object Tracking Dataset link (url) DOI Project Page [BibTex]


no image
Communication Rate Analysis for Event-based State Estimation

(Best student paper finalist)

Ebner, S., Trimpe, S.

In Proceedings of the 13th International Workshop on Discrete Event Systems, May 2016 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


Thumb xl 2pamcompressed
A Lightweight Robotic Arm with Pneumatic Muscles for Robot Learning

Büchler, D., Ott, H., Peters, J.

Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 4086-4092, IEEE, IEEE International Conference on Robotics and Automation, May 2016 (conference)

ICRA16final DOI Project Page [BibTex]

ICRA16final DOI Project Page [BibTex]


no image
Drifting Gaussian Processes with Varying Neighborhood Sizes for Online Model Learning

Meier, F., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2016, IEEE, IEEE International Conference on Robotics and Automation, May 2016 (inproceedings)

[BibTex]

[BibTex]


Thumb xl nao
Ensuring Ethical Behavior from Autonomous Systems

Anderson, M., Anderson, S. L., Berenz, V.

In Artificial Intelligence Applied to Assistive Technologies and Smart Environments, Papers from the 2016 AAAI Workshop, Phoenix, Arizona, USA, February 12, 2016, 2016 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Towards Robust Online Inverse Dynamics Learning

Meier, F., Kappler, D., Ratliff, N., Schaal, S.

Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, IEEE, IROS, 2016 (conference) Accepted

fmeier_iros_2016 [BibTex]

fmeier_iros_2016 [BibTex]


Thumb xl front small
Self-Supervised Regrasping using Spatio-Temporal Tactile Features and Reinforcement Learning

Chebotar, Y., Hausman, K., Su, Z., Sukhatme, G., Schaal, S.

In International Conference on Intelligent Robots and Systems (IROS) 2016, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016 (inproceedings)

pdf video [BibTex]

pdf video [BibTex]


Thumb xl heteroscedasticgp
Modeling Variability of Musculoskeletal Systems with Heteroscedastic Gaussian Processes

Büchler, D., Calandra, R., Peters, J.

Workshop on Neurorobotics, Neural Information Processing Systems (NIPS), 2016 (conference)

NIPS16Neurorobotics [BibTex]

NIPS16Neurorobotics [BibTex]


Thumb xl iser small
Generalizing Regrasping with Supervised Policy Learning

Chebotar, Y., Hausman, K., Kroemer, O., Sukhatme, G., Schaal, S.

In International Symposium on Experimental Robotics (ISER) 2016, International Symposium on Experimental Robotics, 2016 (inproceedings)

pdf video [BibTex]

pdf video [BibTex]


no image
Inertial Sensor-Based Humanoid Joint State Estimation

Rotella, N., Mason, S., Schaal, S., Righetti, L.

In 2016 IEEE International Conference on Robotics and Automation (ICRA), pages: 1825-1831, IEEE, Stockholm, Sweden, 2016 (inproceedings)

Abstract
This work presents methods for the determination of a humanoid robot's joint velocities and accelerations directly from link-mounted Inertial Measurement Units (IMUs) each containing a three-axis gyroscope and a three-axis accelerometer. No information about the global pose of the floating base or its links is required and precise knowledge of the link IMU poses is not necessary due to presented calibration routines. Additionally, a filter is introduced to fuse gyroscope angular velocities with joint position measurements and compensate the computed joint velocities for time-varying gyroscope biases. The resulting joint velocities are subject to less noise and delay than filtered velocities computed from numerical differentiation of joint potentiometer signals, leading to superior performance in joint feedback control as demonstrated in experiments performed on a SARCOS hydraulic humanoid.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Stepping Stabilization Using a Combination of DCM Tracking and Step Adjustment

Khadiv, M., Kleff, S., Herzog, A., Moosavian, S. A. A., Schaal, S., Righetti, L.

In 2016 4th International Conference on Robotics and Mechatronics (ICROM), pages: 130-135, IEEE, Teheran, Iran, 2016 (inproceedings)

Abstract
In this paper, a method for stabilizing biped robots stepping by a combination of Divergent Component of Motion (DCM) tracking and step adjustment is proposed. In this method, the DCM trajectory is generated, consistent with the predefined footprints. Furthermore, a swing foot trajectory modification strategy is proposed to adapt the landing point, using DCM measurement. In order to apply the generated trajectories to the full robot, a Hierarchical Inverse Dynamics (HID) is employed. The HID enables us to use different combinations of the DCM tracking and step adjustment for stabilizing different biped robots. Simulation experiments on two scenarios for two different simulated robots, one with active ankles and the other with passive ankles, are carried out. Simulation results demonstrate the effectiveness of the proposed method for robots with both active and passive ankles.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Structured contact force optimization for kino-dynamic motion generation

Herzog, A., Schaal, S., Righetti, L.

In 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages: 2703-2710, IEEE, Daejeon, South Korea, 2016 (inproceedings)

Abstract
Optimal control approaches in combination with trajectory optimization have recently proven to be a promising control strategy for legged robots. Computationally efficient and robust algorithms were derived using simplified models of the contact interaction between robot and environment such as the linear inverted pendulum model (LIPM). However, as humanoid robots enter more complex environments, less restrictive models become increasingly important. As we leave the regime of linear models, we need to build dedicated solvers that can compute interaction forces together with consistent kinematic plans for the whole-body. In this paper, we address the problem of planning robot motion and interaction forces for legged robots given predefined contact surfaces. The motion generation process is decomposed into two alternating parts computing force and motion plans in coherence. We focus on the properties of the momentum computation leading to sparse optimal control formulations to be exploited by a dedicated solver. In our experiments, we demonstrate that our motion generation algorithm computes consistent contact forces and joint trajectories for our humanoid robot. We also demonstrate the favorable time complexity due to our formulation and composition of the momentum equations.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Balancing and Walking Using Full Dynamics LQR Control With Contact Constraints

Mason, S., Rotella, N., Schaal, S., Righetti, L.

In 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), pages: 63-68, IEEE, Cancun, Mexico, 2016 (inproceedings)

Abstract
Torque control algorithms which consider robot dynamics and contact constraints are important for creating dynamic behaviors for humanoids. As computational power increases, algorithms tend to also increase in complexity. However, it is not clear how much complexity is really required to create controllers which exhibit good performance. In this paper, we study the capabilities of a simple approach based on contact consistent LQR controllers designed around key poses to control various tasks on a humanoid robot. We present extensive experimental results on a hydraulic, torque controlled humanoid performing balancing and stepping tasks. This feedback control approach captures the necessary synergies between the DoFs of the robot to guarantee good control performance. We show that for the considered tasks, it is only necessary to re-linearize the dynamics of the robot at different contact configurations and that increasing the number of LQR controllers along desired trajectories does not improve performance. Our result suggest that very simple controllers can yield good performance competitive with current state of the art, but more complex, optimization-based whole-body controllers. A video of the experiments can be found at https://youtu.be/5T08CNKV1hw.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
On the Effects of Measurement Uncertainty in Optimal Control of Contact Interactions

Ponton, B., Schaal, S., Righetti, L.

In The 12th International Workshop on the Algorithmic Foundations of Robotics WAFR, Berkeley, USA, 2016 (inproceedings)

Abstract
Stochastic Optimal Control (SOC) typically considers noise only in the process model, i.e. unknown disturbances. However, in many robotic applications involving interaction with the environment, such as locomotion and manipulation, uncertainty also comes from lack of precise knowledge of the world, which is not an actual disturbance. We analyze the effects of also considering noise in the measurement model, by devel- oping a SOC algorithm based on risk-sensitive control, that includes the dynamics of an observer in such a way that the control law explicitly de- pends on the current measurement uncertainty. In simulation results on a simple 2D manipulator, we have observed that measurement uncertainty leads to low impedance behaviors, a result in contrast with the effects of process noise that creates stiff behaviors. This suggests that taking into account measurement uncertainty could be a potentially very interesting way to approach problems involving uncertain contact interactions.

link (url) [BibTex]

link (url) [BibTex]


no image
A Convex Model of Momentum Dynamics for Multi-Contact Motion Generation

Ponton, B., Herzog, A., Schaal, S., Righetti, L.

In 2016 IEEE-RAS 16th International Conference on Humanoid Robots Humanoids, pages: 842-849, IEEE, Cancun, Mexico, 2016 (inproceedings)

Abstract
Linear models for control and motion generation of humanoid robots have received significant attention in the past years, not only due to their well known theoretical guarantees, but also because of practical computational advantages. However, to tackle more challenging tasks and scenarios such as locomotion on uneven terrain, a more expressive model is required. In this paper, we are interested in contact interaction-centered motion optimization based on the momentum dynamics model. This model is non-linear and non-convex; however, we find a relaxation of the problem that allows us to formulate it as a single convex quadratically-constrained quadratic program (QCQP) that can be very efficiently optimized and is useful for multi-contact planning. This convex model is then coupled to the optimization of end-effector contact locations using a mixed integer program, which can also be efficiently solved. This becomes relevant e.g. to recover from external pushes, where a predefined stepping plan is likely to fail and an online adaptation of the contact location is needed. The performance of our algorithm is demonstrated in several multi-contact scenarios for a humanoid robot.

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2010


no image
Reinforcement learning of full-body humanoid motor skills

Stulp, F., Buchli, J., Theodorou, E., Schaal, S.

In Humanoid Robots (Humanoids), 2010 10th IEEE-RAS International Conference on, pages: 405-410, December 2010, clmc (inproceedings)

Abstract
Applying reinforcement learning to humanoid robots is challenging because humanoids have a large number of degrees of freedom and state and action spaces are continuous. Thus, most reinforcement learning algorithms would become computationally infeasible and require a prohibitive amount of trials to explore such high-dimensional spaces. In this paper, we present a probabilistic reinforcement learning approach, which is derived from the framework of stochastic optimal control and path integrals. The algorithm, called Policy Improvement with Path Integrals (PI2), has a surprisingly simple form, has no open tuning parameters besides the exploration noise, is model-free, and performs numerically robustly in high dimensional learning problems. We demonstrate how PI2 is able to learn full-body motor skills on a 34-DOF humanoid robot. To demonstrate the generality of our approach, we also apply PI2 in the context of variable impedance control, where both planned trajectories and gain schedules for each joint are optimized simultaneously.

link (url) [BibTex]

2010

link (url) [BibTex]


no image
Relative Entropy Policy Search

Peters, J., Mülling, K., Altun, Y.

In Proceedings of the Twenty-Fourth National Conference on Artificial Intelligence, pages: 1607-1612, (Editors: Fox, M. , D. Poole), AAAI Press, Menlo Park, CA, USA, Twenty-Fourth National Conference on Artificial Intelligence (AAAI-10), July 2010 (inproceedings)

Abstract
Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature convergence and implausible solutions. As first suggested in the context of covariant policy gradients (Bagnell and Schneider 2003), many of these problems may be addressed by constraining the information loss. In this paper, we continue this path of reasoning and suggest the Relative Entropy Policy Search (REPS) method. The resulting method differs significantly from previous policy gradient approaches and yields an exact update step. It works well on typical reinforcement learning benchmark problems.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Reinforcement learning of motor skills in high dimensions: A path integral approach

Theodorou, E., Buchli, J., Schaal, S.

In Robotics and Automation (ICRA), 2010 IEEE International Conference on, pages: 2397-2403, May 2010, clmc (inproceedings)

Abstract
Reinforcement learning (RL) is one of the most general approaches to learning control. Its applicability to complex motor systems, however, has been largely impossible so far due to the computational difficulties that reinforcement learning encounters in high dimensional continuous state-action spaces. In this paper, we derive a novel approach to RL for parameterized control policies based on the framework of stochastic optimal control with path integrals. While solidly grounded in optimal control theory and estimation theory, the update equations for learning are surprisingly simple and have no danger of numerical instabilities as neither matrix inversions nor gradient learning rates are required. Empirical evaluations demonstrate significant performance improvements over gradient-based policy learning and scalability to high-dimensional control problems. Finally, a learning experiment on a robot dog illustrates the functionality of our algorithm in a real-world scenario. We believe that our new algorithm, Policy Improvement with Path Integrals (PI2), offers currently one of the most efficient, numerically robust, and easy to implement algorithms for RL in robotics.

link (url) [BibTex]

link (url) [BibTex]


no image
Inverse dynamics control of floating base systems using orthogonal decomposition

Mistry, M., Buchli, J., Schaal, S.

In Robotics and Automation (ICRA), 2010 IEEE International Conference on, pages: 3406-3412, May 2010, clmc (inproceedings)

Abstract
Model-based control methods can be used to enable fast, dexterous, and compliant motion of robots without sacrificing control accuracy. However, implementing such techniques on floating base robots, e.g., humanoids and legged systems, is non-trivial due to under-actuation, dynamically changing constraints from the environment, and potentially closed loop kinematics. In this paper, we show how to compute the analytically correct inverse dynamics torques for model-based control of sufficiently constrained floating base rigid-body systems, such as humanoid robots with one or two feet in contact with the environment. While our previous inverse dynamics approach relied on an estimation of contact forces to compute an approximate inverse dynamics solution, here we present an analytically correct solution by using an orthogonal decomposition to project the robot dynamics onto a reduced dimensional space, independent of contact forces. We demonstrate the feasibility and robustness of our approach on a simulated floating base bipedal humanoid robot and an actual robot dog locomoting over rough terrain.

link (url) [BibTex]

link (url) [BibTex]


no image
Fast, robust quadruped locomotion over challenging terrain

Kalakrishnan, M., Buchli, J., Pastor, P., Mistry, M., Schaal, S.

In Robotics and Automation (ICRA), 2010 IEEE International Conference on, pages: 2665-2670, May 2010, clmc (inproceedings)

Abstract
We present a control architecture for fast quadruped locomotion over rough terrain. We approach the problem by decomposing it into many sub-systems, in which we apply state-of-the-art learning, planning, optimization and control techniques to achieve robust, fast locomotion. Unique features of our control strategy include: (1) a system that learns optimal foothold choices from expert demonstration using terrain templates, (2) a body trajectory optimizer based on the Zero-Moment Point (ZMP) stability criterion, and (3) a floating-base inverse dynamics controller that, in conjunction with force control, allows for robust, compliant locomotion over unperceived obstacles. We evaluate the performance of our controller by testing it on the LittleDog quadruped robot, over a wide variety of rough terrain of varying difficulty levels. We demonstrate the generalization ability of this controller by presenting test results from an independent external test team on terrains that have never been shown to us.

link (url) [BibTex]

link (url) [BibTex]


no image
Are reaching movements planned in kinematic or dynamic coordinates?

Ellmer, A., Schaal, S.

In Abstracts of Neural Control of Movement Conference (NCM 2010), Naples, Florida, 2010, 2010, clmc (inproceedings)

Abstract
Whether human reaching movements are planned and optimized in kinematic (task space) or dynamic (joint or muscle space) coordinates is still an issue of debate. The first hypothesis implies that a planner produces a desired end-effector position at each point in time during the reaching movement, whereas the latter hypothesis includes the dynamics of the muscular-skeletal control system to produce a continuous end-effector trajectory. Previous work by Wolpert et al (1995) showed that when subjects were led to believe that their straight reaching paths corresponded to curved paths as shown on a computer screen, participants adapted the true path of their hand such that they would visually perceive a straight line in visual space, despite that they actually produced a curved path. These results were interpreted as supporting the stance that reaching trajectories are planned in kinematic coordinates. However, this experiment could only demonstrate that adaptation to altered paths, i.e. the position of the end-effector, did occur, but not that the precise timing of end-effector position was equally planned, i.e., the trajectory. Our current experiment aims at filling this gap by explicitly testing whether position over time, i.e. velocity, is a property of reaching movements that is planned in kinematic coordinates. In the current experiment, the velocity profiles of cursor movements corresponding to the participant's hand motions were skewed either to the left or to the right; the path itself was left unaltered. We developed an adaptation paradigm, where the skew of the velocity profile was introduced gradually and participants reported no awareness of any manipulation. Preliminary results indicate that the true hand motion of participants did not alter, i.e. there was no adaptation so as to counterbalance the introduced skew. However, for some participants, peak hand velocities were lowered for higher skews, which suggests that participants interpreted the manipulation as mere noise due to variance in their own movement. In summary, for a visuomotor transformation task, the hypothesis of a planned continuous end-effector trajectory predicts adaptation to a modified velocity profile. The current experiment found no systematic adaptation under such transformation, but did demonstrate an effect that is more in accordance that subjects could not perceive the manipulation and rather interpreted as an increase of noise.

[BibTex]

[BibTex]


no image
Optimality in Neuromuscular Systems

Theodorou, E. A., Valero-Cuevas, F.

In 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2010, clmc (inproceedings)

Abstract
Abstract? We provide an overview of optimal control meth- ods to nonlinear neuromuscular systems and discuss their lim- itations. Moreover we extend current optimal control methods to their application to neuromuscular models with realistically numerous musculotendons; as most prior work is limited to torque-driven systems. Recent work on computational motor control has explored the used of control theory and esti- mation as a conceptual tool to understand the underlying computational principles of neuromuscular systems. After all, successful biological systems regularly meet conditions for stability, robustness and performance for multiple classes of complex tasks. Among a variety of proposed control theory frameworks to explain this, stochastic optimal control has become a dominant framework to the point of being a standard computational technique to reproduce kinematic trajectories of reaching movements (see [12]) In particular, we demonstrate the application of optimal control to a neuromuscular model of the index finger with all seven musculotendons producing a tapping task. Our simu- lations include 1) a muscle model that includes force- length and force-velocity characteristics; 2) an anatomically plausible biomechanical model of the index finger that includes a tendi- nous network for the extensor mechanism and 3) a contact model that is based on a nonlinear spring-damper attached at the end effector of the index finger. We demonstrate that it is feasible to apply optimal control to systems with realistically large state vectors and conclude that, while optimal control is an adequate formalism to create computational models of neuro- musculoskeletal systems, there remain important challenges and limitations that need to be considered and overcome such as contact transitions, curse of dimensionality, and constraints on states and controls.

PDF [BibTex]

PDF [BibTex]


no image
Learning Policy Improvements with Path Integrals

Theodorou, E. A., Buchli, J., Schaal, S.

In International Conference on Artificial Intelligence and Statistics (AISTATS 2010), 2010, clmc (inproceedings)

Abstract
With the goal to generate more scalable algo- rithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classi- cal techniques from optimal control and dy- namic programming with modern learning techniques from statistical estimation the- ory. In this vein, this paper suggests the framework of stochastic optimal control with path integrals to derive a novel approach to RL with parametrized policies. While solidly grounded in value function estimation and optimal control based on the stochastic Hamilton-Jacobi-Bellman (HJB) equations, policy improvements can be transformed into an approximation problem of a path inte- gral which has no open parameters other than the exploration noise. The resulting algorithm can be conceived of as model- based, semi-model-based, or even model free, depending on how the learning problem is structured. Our new algorithm demon- strates interesting similarities with previous RL research in the framework of proba- bility matching and provides intuition why the slightly heuristically motivated proba- bility matching approach can actually per- form well. Empirical evaluations demon- strate significant performance improvements over gradient-based policy learning and scal- ability to high-dimensional control problems. We believe that Policy Improvement with Path Integrals (PI2) offers currently one of the most efficient, numerically robust, and easy to implement algorithms for RL based on trajectory roll-outs.

PDF [BibTex]

PDF [BibTex]


no image
Learning optimal control solutions: a path integral approach

Theodorou, E., Schaal, S.

In Abstracts of Neural Control of Movement Conference (NCM 2010), Naples, Florida, 2010, 2010, clmc (inproceedings)

Abstract
Investigating principles of human motor control in the framework of optimal control has had a long tradition in neural control of movement, and has recently experienced a new surge of investigations. Ideally, optimal control problems are addresses as a reinforcement learning (RL) problem, which would allow to investigate both the process of acquiring an optimal control solution as well as the solution itself. Unfortunately, the applicability of RL to complex neural and biomechanics systems has been largely impossible so far due to the computational difficulties that arise in high dimensional continuous state-action spaces. As a way out, research has focussed on computing optimal control solutions based on iterative optimal control methods that are based on linear and quadratic approximations of dynamical models and cost functions. These methods require perfect knowledge of the dynamics and cost functions while they are based on gradient and Newton optimization schemes. Their applicability is also restricted to low dimensional problems due to problematic convergence in high dimensions. Moreover, the process of computing the optimal solution is removed from the learning process that might be plausible in biology. In this work, we present a new reinforcement learning method for learning optimal control solutions or motor control. This method, based on the framework of stochastic optimal control with path integrals, has a very solid theoretical foundation, while resulting in surprisingly simple learning algorithms. It is also possible to apply this approach without knowledge of the system model, and to use a wide variety of complex nonlinear cost functions for optimization. We illustrate the theoretical properties of this approach and its applicability to learning motor control tasks for reaching movements and locomotion studies. We discuss its applicability to learning desired trajectories, variable stiffness control (co-contraction), and parameterized control policies. We also investigate the applicability to signal dependent noise control systems. We believe that the suggested method offers one of the easiest to use approaches to learning optimal control suggested in the literature so far, which makes it ideally suited for computational investigations of biological motor control.

[BibTex]

[BibTex]


no image
Constrained Accelerations for Controlled Geometric Reduction: Sagittal-Plane Decoupling for Bipedal Locomotion

Gregg, R., Righetti, L., Buchli, J., Schaal, S.

In 2010 10th IEEE-RAS International Conference on Humanoid Robots, pages: 1-7, IEEE, Nashville, USA, 2010 (inproceedings)

Abstract
Energy-shaping control methods have produced strong theoretical results for asymptotically stable 3D bipedal dynamic walking in the literature. In particular, geometric controlled reduction exploits robot symmetries to control momentum conservation laws that decouple the sagittal-plane dynamics, which are easier to stabilize. However, the associated control laws require high-dimensional matrix inverses multiplied with complicated energy-shaping terms, often making these control theories difficult to apply to highly-redundant humanoid robots. This paper presents a first step towards the application of energy-shaping methods on real robots by casting controlled reduction into a framework of constrained accelerations for inverse dynamics control. By representing momentum conservation laws as constraints in acceleration space, we construct a general expression for desired joint accelerations that render the constraint surface invariant. By appropriately choosing an orthogonal projection, we show that the unconstrained (reduced) dynamics are decoupled from the constrained dynamics. Any acceleration-based controller can then be used to stabilize this planar subsystem, including passivity-based methods. The resulting control law is surprisingly simple and represents a practical way to employ control theoretic stability results in robotic platforms. Simulated walking of a 3D compass-gait biped show correspondence between the new and original controllers, and simulated motions of a 16-DOF humanoid demonstrate the applicability of this method.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Variable impedance control - a reinforcement learning approach

Buchli, J., Theodorou, E., Stulp, F., Schaal, S.

In Robotics Science and Systems (2010), Zaragoza, Spain, June 27-30, 2010, clmc (inproceedings)

Abstract
One of the hallmarks of the performance, versatility, and robustness of biological motor control is the ability to adapt the impedance of the overall biomechanical system to different task requirements and stochastic disturbances. A transfer of this principle to robotics is desirable, for instance to enable robots to work robustly and safely in everyday human environments. It is, however, not trivial to derive variable impedance controllers for practical high DOF robotic tasks. In this contribution, we accomplish such gain scheduling with a reinforcement learning approach algorithm, PI2 (Policy Improvement with Path Integrals). PI2 is a model-free, sampling based learning method derived from first principles of optimal control. The PI2 algorithm requires no tuning of algorithmic parameters besides the exploration noise. The designer can thus fully focus on cost function design to specify the task. From the viewpoint of robotics, a particular useful property of PI2 is that it can scale to problems of many DOFs, so that RL on real robotic systems becomes feasible. We sketch the PI2 algorithm and its theoretical properties, and how it is applied to gain scheduling. We evaluate our approach by presenting results on two different simulated robotic systems, a 3-DOF Phantom Premium Robot and a 6-DOF Kuka Lightweight Robot. We investigate tasks where the optimal strategy requires both tuning of the impedance of the end-effector, and tuning of a reference trajectory. The results show that we can use path integral based RL not only for planning but also to derive variable gain feedback controllers in realistic scenarios. Thus, the power of variable impedance control is made available to a wide variety of robotic systems and practical applications.

link (url) [BibTex]

link (url) [BibTex]


no image
Inverse dynamics with optimal distribution of ground reaction forces for legged robot

Righetti, L., Buchli, J., Mistry, M., Schaal, S.

In Proceedings of the 13th International Conference on Climbing and Walking Robots (CLAWAR), pages: 580-587, Nagoya, Japan, sep 2010 (inproceedings)

Abstract
Contact interaction with the environment is crucial in the design of locomotion controllers for legged robots, to prevent slipping for example. Therefore, it is of great importance to be able to control the effects of the robots movements on the contact reaction forces. In this contribution, we extend a recent inverse dynamics algorithm for floating base robots to optimize the distribution of contact forces while achieving precise trajectory tracking. The resulting controller is algorithmically simple as compared to other approaches. Numerical simulations show that this result significantly increases the range of possible movements of a humanoid robot as compared to the previous inverse dynamics algorithm. We also present a simplification of the result where no inversion of the inertia matrix is needed which is particularly relevant for practical use on a real robot. Such an algorithm becomes interesting for agile locomotion of robots on difficult terrains where the contacts with the environment are critical, such as walking over rough or slippery terrain.

DOI [BibTex]

DOI [BibTex]

2007


no image
Towards Machine Learning of Motor Skills

Peters, J., Schaal, S., Schölkopf, B.

In Proceedings of Autonome Mobile Systeme (AMS), pages: 138-144, (Editors: K Berns and T Luksch), 2007, clmc (inproceedings)

Abstract
Autonomous robots that can adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s, however, made it clear that an approach purely based on reasoning or human insights would not be able to model all the perceptuomotor tasks that a robot should fulfill. Instead, new hope was put in the growing wake of machine learning that promised fully adaptive control algorithms which learn both by observation and trial-and-error. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach to motor skill learning in order to get one step closer towards human-like performance. For doing so, we study two ma jor components for such an approach, i.e., firstly, a theoretically well-founded general approach to representing the required control structures for task representation and execution and, secondly, appropriate learning algorithms which can be applied in this setting.

PDF DOI [BibTex]

2007

PDF DOI [BibTex]


no image
Reinforcement Learning for Optimal Control of Arm Movements

Theodorou, E., Peters, J., Schaal, S.

In Abstracts of the 37st Meeting of the Society of Neuroscience., Neuroscience, 2007, clmc (inproceedings)

Abstract
Every day motor behavior consists of a plethora of challenging motor skills from discrete movements such as reaching and throwing to rhythmic movements such as walking, drumming and running. How this plethora of motor skills can be learned remains an open question. In particular, is there any unifying computa-tional framework that could model the learning process of this variety of motor behaviors and at the same time be biologically plausible? In this work we aim to give an answer to these questions by providing a computational framework that unifies the learning mechanism of both rhythmic and discrete movements under optimization criteria, i.e., in a non-supervised trial-and-error fashion. Our suggested framework is based on Reinforcement Learning, which is mostly considered as too costly to be a plausible mechanism for learning com-plex limb movement. However, recent work on reinforcement learning with pol-icy gradients combined with parameterized movement primitives allows novel and more efficient algorithms. By using the representational power of such mo-tor primitives we show how rhythmic motor behaviors such as walking, squash-ing and drumming as well as discrete behaviors like reaching and grasping can be learned with biologically plausible algorithms. Using extensive simulations and by using different reward functions we provide results that support the hy-pothesis that Reinforcement Learning could be a viable candidate for motor learning of human motor behavior when other learning methods like supervised learning are not feasible.

[BibTex]

[BibTex]


no image
Reinforcement learning by reward-weighted regression for operational space control

Peters, J., Schaal, S.

In Proceedings of the 24th Annual International Conference on Machine Learning, pages: 745-750, ICML, 2007, clmc (inproceedings)

Abstract
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-base reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Policy gradient methods for machine learning

Peters, J., Theodorou, E., Schaal, S.

In Proceedings of the 14th INFORMS Conference of the Applied Probability Society, pages: 97-98, Eindhoven, Netherlands, July 9-11, 2007, 2007, clmc (inproceedings)

Abstract
We present an in-depth survey of policy gradient methods as they are used in the machine learning community for optimizing parameterized, stochastic control policies in Markovian systems with respect to the expected reward. Despite having been developed separately in the reinforcement learning literature, policy gradient methods employ likelihood ratio gradient estimators as also suggested in the stochastic simulation optimization community. It is well-known that this approach to policy gradient estimation traditionally suffers from three drawbacks, i.e., large variance, a strong dependence on baseline functions and a inefficient gradient descent. In this talk, we will present a series of recent results which tackles each of these problems. The variance of the gradient estimation can be reduced significantly through recently introduced techniques such as optimal baselines, compatible function approximations and all-action gradients. However, as even the analytically obtainable policy gradients perform unnaturally slow, it required the step from ÔvanillaÕ policy gradient methods towards natural policy gradients in order to overcome the inefficiency of the gradient descent. This development resulted into the Natural Actor-Critic architecture which can be shown to be very efficient in application to motor primitive learning for robotics.

[BibTex]

[BibTex]


no image
Policy Learning for Motor Skills

Peters, J., Schaal, S.

In Proceedings of 14th International Conference on Neural Information Processing (ICONIP), pages: 233-242, (Editors: Ishikawa, M. , K. Doya, H. Miyamoto, T. Yamakawa), 2007, clmc (inproceedings)

Abstract
Policy learning which allows autonomous robots to adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach policy learning with the goal of an application to motor skill refinement in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, we study policy learning algorithms which can be applied in the general setting of motor skill learning, and, secondly, we study a theoretically well-founded general approach to representing the required control structures for task representation and execution.

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Reinforcement learning for operational space control

Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Conference on Robotics and Automation, pages: 2111-2116, IEEE Computer Society, ICRA, 2007, clmc (inproceedings)

Abstract
While operational space control is of essential importance for robotics and well-understood from an analytical point of view, it can be prohibitively hard to achieve accurate control in face of modeling errors, which are inevitable in complex robots, e.g., humanoid robots. In such cases, learning control methods can offer an interesting alternative to analytical control algorithms. However, the resulting supervised learning problem is ill-defined as it requires to learn an inverse mapping of a usually redundant system, which is well known to suffer from the property of non-convexity of the solution space, i.e., the learning system could generate motor commands that try to steer the robot into physically impossible configurations. The important insight that many operational space control algorithms can be reformulated as optimal control problems, however, allows addressing this inverse learning problem in the framework of reinforcement learning. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-based reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Using reward-weighted regression for reinforcement learning of task space control

Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pages: 262-267, Honolulu, Hawaii, April 1-5, 2007, 2007, clmc (inproceedings)

Abstract
In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, `vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark

Riedmiller, M., Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pages: 254-261, ADPRL, 2007, clmc (inproceedings)

Abstract
In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, `vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

PDF [BibTex]

PDF [BibTex]