Header logo is ei


2007


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]

2007

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
Relative Entropy Policy Search

Peters, J.

CLMC Technical Report: TR-CLMC-2007-2, Computational Learning and Motor Control Lab, Los Angeles, CA, 2007, clmc (techreport)

Abstract
This technical report describes a cute idea of how to create new policy search approaches. It directly relates to the Natural Actor-Critic methods but allows the derivation of one shot solutions. Future work may include the application to interesting problems.

PDF link (url) [BibTex]

PDF link (url) [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]

2001


no image
Regularized principal manifolds

Smola, A., Mika, S., Schölkopf, B., Williamson, R.

Journal of Machine Learning Research, 1, pages: 179-209, June 2001 (article)

Abstract
Many settings of unsupervised learning can be viewed as quantization problems - the minimization of the expected quantization error subject to some restrictions. This allows the use of tools such as regularization from the theory of (supervised) risk minimization for unsupervised learning. This setting turns out to be closely related to principal curves, the generative topographic map, and robust coding. We explore this connection in two ways: (1) we propose an algorithm for finding principal manifolds that can be regularized in a variety of ways; and (2) we derive uniform convergence bounds and hence bounds on the learning rates of the algorithm. In particular, we give bounds on the covering numbers which allows us to obtain nearly optimal learning rates for certain types of regularization operators. Experimental results demonstrate the feasibility of the approach.

PDF [BibTex]

2001

PDF [BibTex]


no image
Variationsverfahren zur Untersuchung von Grundzustandseigenschaften des Ein-Band Hubbard-Modells

Eichhorn, J.

Biologische Kybernetik, Technische Universität Dresden, Dresden/Germany, May 2001 (diplomathesis)

Abstract
Using different modifications of a new variational approach, statical groundstate properties of the one-band Hubbard model such as energy and staggered magnetisation are calculated. By taking into account additional fluctuations, the method ist gradually improved so that a very good description of the energy in one and two dimensions can be achieved. After a detailed discussion of the application in one dimension, extensions for two dimensions are introduced. By use of a modified version of the variational ansatz in particular a description of the quantum phase transition for the magnetisation should be possible.

PostScript [BibTex]

PostScript [BibTex]


no image
The psychometric function: II. Bootstrap-based confidence intervals and sampling

Wichmann, F., Hill, N.

Perception and Psychophysics, 63 (8), pages: 1314-1329, 2001 (article)

PDF [BibTex]

PDF [BibTex]


no image
The psychometric function: I. Fitting, sampling and goodness-of-fit

Wichmann, F., Hill, N.

Perception and Psychophysics, 63 (8), pages: 1293-1313, 2001 (article)

Abstract
The psychometric function relates an observer'sperformance to an independent variable, usually some physical quantity of a stimulus in a psychophysical task. This paper, together with its companion paper (Wichmann & Hill, 2001), describes an integrated approach to (1) fitting psychometric functions, (2) assessing the goodness of fit, and (3) providing confidence intervals for the function'sparameters and other estimates derived from them, for the purposes of hypothesis testing. The present paper deals with the first two topics, describing a constrained maximum-likelihood method of parameter estimation and developing several goodness-of-fit tests. Using Monte Carlo simulations, we deal with two specific difficulties that arise when fitting functions to psychophysical data. First, we note that human observers are prone to stimulus-independent errors (or lapses ). We show that failure to account for this can lead to serious biases in estimates of the psychometric function'sparameters and illustrate how the problem may be overcome. Second, we note that psychophysical data sets are usually rather small by the standards required by most of the commonly applied statistical tests. We demonstrate the potential errors of applying traditional X^2 methods to psychophysical data and advocate use of Monte Carlo resampling techniques that do not rely on asymptotic theory. We have made available the software to implement our methods

PDF [BibTex]

PDF [BibTex]


no image
Unsupervised Segmentation and Classification of Mixtures of Markovian Sources

Seldin, Y., Bejerano, G., Tishby, N.

In The 33rd Symposium on the Interface of Computing Science and Statistics (Interface 2001 - Frontiers in Data Mining and Bioinformatics), pages: 1-15, 33rd Symposium on the Interface of Computing Science and Statistics (Interface - Frontiers in Data Mining and Bioinformatics), 2001 (inproceedings)

Abstract
We describe a novel algorithm for unsupervised segmentation of sequences into alternating Variable Memory Markov sources, first presented in [SBT01]. The algorithm is based on competitive learning between Markov models, when implemented as Prediction Suffix Trees [RST96] using the MDL principle. By applying a model clustering procedure, based on rate distortion theory combined with deterministic annealing, we obtain a hierarchical segmentation of sequences between alternating Markov sources. The method is applied successfully to unsupervised segmentation of multilingual texts into languages where it is able to infer correctly both the number of languages and the language switching points. When applied to protein sequence families (results of the [BSMT01] work), we demonstrate the method‘s ability to identify biologically meaningful sub-sequences within the proteins, which correspond to signatures of important functional sub-units called domains. Our approach to proteins classification (through the obtained signatures) is shown to have both conceptual and practical advantages over the currently used methods.

PDF Web [BibTex]

PDF Web [BibTex]


no image
Markovian domain fingerprinting: statistical segmentation of protein sequences

Bejerano, G., Seldin, Y., Margalit, H., Tishby, N.

Bioinformatics, 17(10):927-934, 2001 (article)

PDF Web [BibTex]

PDF Web [BibTex]


no image
Unsupervised Sequence Segmentation by a Mixture of Switching Variable Memory Markov Sources

Seldin, Y., Bejerano, G., Tishby, N.

In In the proceeding of the 18th International Conference on Machine Learning (ICML 2001), pages: 513-520, 18th International Conference on Machine Learning (ICML), 2001 (inproceedings)

Abstract
We present a novel information theoretic algorithm for unsupervised segmentation of sequences into alternating Variable Memory Markov sources. The algorithm is based on competitive learning between Markov models, when implemented as Prediction Suffix Trees (Ron et al., 1996) using the MDL principle. By applying a model clustering procedure, based on rate distortion theory combined with deterministic annealing, we obtain a hierarchical segmentation of sequences between alternating Markov sources. The algorithm seems to be self regulated and automatically avoids over segmentation. The method is applied successfully to unsupervised segmentation of multilingual texts into languages where it is able to infer correctly both the number of languages and the language switching points. When applied to protein sequence families, we demonstrate the method‘s ability to identify biologically meaningful sub-sequences within the proteins, which correspond to important functional sub-units called domains.

PDF [BibTex]

PDF [BibTex]


no image
Inference Principles and Model Selection

Buhmann, J., Schölkopf, B.

(01301), Dagstuhl Seminar, 2001 (techreport)

Web [BibTex]

Web [BibTex]

1996


no image
Incorporating invariances in support vector learning machines

Schölkopf, B., Burges, C., Vapnik, V.

In Artificial Neural Networks: ICANN 96, LNCS vol. 1112, pages: 47-52, (Editors: C von der Malsburg and W von Seelen and JC Vorbrüggen and B Sendhoff), Springer, Berlin, Germany, 6th International Conference on Artificial Neural Networks, July 1996, volume 1112 of Lecture Notes in Computer Science (inproceedings)

Abstract
Developed only recently, support vector learning machines achieve high generalization ability by minimizing a bound on the expected test error; however, so far there existed no way of adding knowledge about invariances of a classification problem at hand. We present a method of incorporating prior knowledge about transformation invariances by applying transformations to support vectors, the training examples most critical for determining the classification boundary.

PDF DOI [BibTex]

1996

PDF DOI [BibTex]