Header logo is

478 results (View BibTeX file of all listed publications)

2007

no image
Fast Kernel ICA using an Approximate Newton Method

Shen, H., Jegelka, S., Gretton, A.

In JMLR Workshop and Conference Proceedings Volume 2: AISTATS 2007, pages: 476-483, (Editors: Meila, M. , X. Shen), MIT Press, Cambridge, MA, USA, 11th International Conference on Artificial Intelligence and Statistics, March 2007 (inproceedings)

Abstract
Recent approaches to independent component analysis (ICA) have used kernel independence measures to obtain very good performance, particularly where classical methods experience difficulty (for instance, sources with near-zero kurtosis). We present Fast Kernel ICA (FastKICA), a novel optimisation technique for one such kernel independence measure, the Hilbert-Schmidt independence criterion (HSIC). Our search procedure uses an approximate Newton method on the special orthogonal group, where we estimate the Hessian locally about independence. We employ incomplete Cholesky decomposition to efficiently compute the gradient and approximate Hessian. FastKICA results in more accurate solutions at a given cost compared with gradient descent, and is relatively insensitive to local minima when initialised far from independence. These properties allow kernel approaches to be extended to problems with larger numbers of sources and observations. Our method is competitive with other modern and classical ICA approaches in both speed and accuracy.

ei

PDF Web [BibTex]

2007

ei Shen, H., Jegelka, S., Gretton, A. Fast Kernel ICA using an Approximate Newton Method In JMLR Workshop and Conference Proceedings Volume 2: AISTATS 2007, pages: 476-483, (Editors: Meila, M. , X. Shen), MIT Press, Cambridge, MA, USA, 11th International Conference on Artificial Intelligence and Statistics, March 2007 (inproceedings)

PDF Web [BibTex]

no image
Neighborhood Property based Pattern Selection for Support Vector Machines

Shin, H., Cho, S.

Neural Computation, 19(3):816-855, March 2007 (article)

Abstract
The support vector machine (SVM) has been spotlighted in the machine learning community because of its theoretical soundness and practical performance. When applied to a large data set, however, it requires a large memory and a long time for training. To cope with the practical difficulty, we propose a pattern selection algorithm based on neighborhood properties. The idea is to select only the patterns that are likely to be located near the decision boundary. Those patterns are expected to be more informative than the randomly selected patterns. The experimental results provide promising evidence that it is possible to successfully employ the proposed algorithm ahead of SVM training.

ei

PDF Web DOI [BibTex]

ei Shin, H., Cho, S. Neighborhood Property based Pattern Selection for Support Vector Machines Neural Computation, 19(3):816-855, March 2007 (article)

PDF Web DOI [BibTex]

no image
Training a Support Vector Machine in the Primal

Chapelle, O.

Neural Computation, 19(5):1155-1178, March 2007 (article)

Abstract
Most literature on Support Vector Machines (SVMs) concentrate on the dual optimization problem. In this paper, we would like to point out that the primal problem can also be solved efficiently, both for linear and non-linear SVMs, and that there is no reason for ignoring this possibilty. On the contrary, from the primal point of view new families of algorithms for large scale SVM training can be investigated.

ei

PDF Web DOI [BibTex]

ei Chapelle, O. Training a Support Vector Machine in the Primal Neural Computation, 19(5):1155-1178, March 2007 (article)

PDF Web DOI [BibTex]

no image
Transductive Classification via Local Learning Regularization

Wu, M., Schölkopf, B.

In JMLR Workshop and Conference Proceedings Volume 2: AISTATS 2007, pages: 628-635, (Editors: M Meila and X Shen), 11th International Conference on Artificial Intelligence and Statistics, March 2007 (inproceedings)

Abstract
The idea of local learning, classifying a particular point based on its neighbors, has been successfully applied to supervised learning problems. In this paper, we adapt it for Transductive Classification (TC) problems. Specifically, we formulate a Local Learning Regularizer (LL-Reg) which leads to a solution with the property that the label of each data point can be well predicted based on its neighbors and their labels. For model selection, an efficient way to compute the leave-one-out classification error is provided for the proposed and related algorithms. Experimental results using several benchmark datasets illustrate the effectiveness of the proposed approach.

ei

PDF Web [BibTex]

ei Wu, M., Schölkopf, B. Transductive Classification via Local Learning Regularization In JMLR Workshop and Conference Proceedings Volume 2: AISTATS 2007, pages: 628-635, (Editors: M Meila and X Shen), 11th International Conference on Artificial Intelligence and Statistics, March 2007 (inproceedings)

PDF Web [BibTex]

no image
Improving the Caenorhabditis elegans Genome Annotation Using Machine Learning

Rätsch, G., Sonnenburg, S., Srinivasan, J., Witte, H., Müller, K., Sommer, R., Schölkopf, B.

PLoS Computational Biology, 3(2, e20):0313-0322, February 2007 (article)

ei

PDF DOI [BibTex]

ei Rätsch, G., Sonnenburg, S., Srinivasan, J., Witte, H., Müller, K., Sommer, R., Schölkopf, B. Improving the Caenorhabditis elegans Genome Annotation Using Machine Learning PLoS Computational Biology, 3(2, e20):0313-0322, February 2007 (article)

PDF DOI [BibTex]

no image
The Independent Components of Natural Images are Perceptually Dependent

Bethge, M., Wiecki, T., Wichmann, F.

In Human Vision and Electronic Imaging XII, pages: 1-12, (Editors: Rogowitz, B. E.), SPIE, Bellingham, WA, USA, SPIE Human Vision and Electronic Imaging Conference, February 2007 (inproceedings)

Abstract
The independent components of natural images are a set of linear filters which are optimized for statistical independence. With such a set of filters images can be represented without loss of information. Intriguingly, the filter shapes are localized, oriented, and bandpass, resembling important properties of V1 simple cell receptive fields. Here we address the question of whether the independent components of natural images are also perceptually less dependent than other image components. We compared the pixel basis, the ICA basis and the discrete cosine basis by asking subjects to interactively predict missing pixels (for the pixel basis) or to predict the coefficients of ICA and DCT basis functions in patches of natural images. Like Kersten (1987) we find the pixel basis to be perceptually highly redundant but perhaps surprisingly, the ICA basis showed significantly higher perceptual dependencies than the DCT basis. This shows a dissociation between statistical and perceptual dependence measures.

ei

PDF Web DOI [BibTex]

ei Bethge, M., Wiecki, T., Wichmann, F. The Independent Components of Natural Images are Perceptually Dependent In Human Vision and Electronic Imaging XII, pages: 1-12, (Editors: Rogowitz, B. E.), SPIE, Bellingham, WA, USA, SPIE Human Vision and Electronic Imaging Conference, February 2007 (inproceedings)

PDF Web DOI [BibTex]

no image
Statistical Consistency of Kernel Canonical Correlation Analysis

Fukumizu, K., Bach, F., Gretton, A.

Journal of Machine Learning Research, 8, pages: 361-383, February 2007 (article)

Abstract
While kernel canonical correlation analysis (CCA) has been applied in many contexts, the convergence of finite sample estimates of the associated functions to their population counterparts has not yet been established. This paper gives a mathematical proof of the statistical convergence of kernel CCA, providing a theoretical justification for the method. The proof uses covariance operators defined on reproducing kernel Hilbert spaces, and analyzes the convergence of their empirical estimates of finite rank to their population counterparts, which can have infinite rank. The result also gives a sufficient condition for convergence on the regularization coefficient involved in kernel CCA: this should decrease as n^{-1/3}, where n is the number of data.

ei

PDF [BibTex]

ei Fukumizu, K., Bach, F., Gretton, A. Statistical Consistency of Kernel Canonical Correlation Analysis Journal of Machine Learning Research, 8, pages: 361-383, February 2007 (article)

PDF [BibTex]

no image
Unsupervised learning of a steerable basis for invariant image representations

Bethge, M., Gerwinn, S., Macke, J.

In Human Vision and Electronic Imaging XII, pages: 1-12, (Editors: Rogowitz, B. E.), SPIE, Bellingham, WA, USA, SPIE Human Vision and Electronic Imaging Conference, February 2007 (inproceedings)

Abstract
There are two aspects to unsupervised learning of invariant representations of images: First, we can reduce the dimensionality of the representation by finding an optimal trade-off between temporal stability and informativeness. We show that the answer to this optimization problem is generally not unique so that there is still considerable freedom in choosing a suitable basis. Which of the many optimal representations should be selected? Here, we focus on this second aspect, and seek to find representations that are invariant under geometrical transformations occuring in sequences of natural images. We utilize ideas of steerability and Lie groups, which have been developed in the context of filter design. In particular, we show how an anti-symmetric version of canonical correlation analysis can be used to learn a full-rank image basis which is steerable with respect to rotations. We provide a geometric interpretation of this algorithm by showing that it finds the two-dimensional eigensubspaces of the avera ge bivector. For data which exhibits a variety of transformations, we develop a bivector clustering algorithm, which we use to learn a basis of generalized quadrature pairs (i.e. complex cells) from sequences of natural images.

ei

PDF Web DOI [BibTex]

ei Bethge, M., Gerwinn, S., Macke, J. Unsupervised learning of a steerable basis for invariant image representations In Human Vision and Electronic Imaging XII, pages: 1-12, (Editors: Rogowitz, B. E.), SPIE, Bellingham, WA, USA, SPIE Human Vision and Electronic Imaging Conference, February 2007 (inproceedings)

PDF Web DOI [BibTex]

no image
A Subspace Kernel for Nonlinear Feature Extraction

Wu, M., Farquhar, J.

In IJCAI-07, pages: 1125-1130, (Editors: Veloso, M. M.), AAAI Press, Menlo Park, CA, USA, International Joint Conference on Artificial Intelligence, January 2007 (inproceedings)

Abstract
Kernel based nonlinear Feature Extraction (KFE) or dimensionality reduction is a widely used pre-processing step in pattern classification and data mining tasks. Given a positive definite kernel function, it is well known that the input data are implicitly mapped to a feature space with usually very high dimensionality. The goal of KFE is to find a low dimensional subspace of this feature space, which retains most of the information needed for classification or data analysis. In this paper, we propose a subspace kernel based on which the feature extraction problem is transformed to a kernel parameter learning problem. The key observation is that when projecting data into a low dimensional subspace of the feature space, the parameters that are used for describing this subspace can be regarded as the parameters of the kernel function between the projected data. Therefore current kernel parameter learning methods can be adapted to optimize this parameterized kernel function. Experimental results are provided to validate the effectiveness of the proposed approach.

ei

PDF Web [BibTex]

ei Wu, M., Farquhar, J. A Subspace Kernel for Nonlinear Feature Extraction In IJCAI-07, pages: 1125-1130, (Editors: Veloso, M. M.), AAAI Press, Menlo Park, CA, USA, International Joint Conference on Artificial Intelligence, January 2007 (inproceedings)

PDF Web [BibTex]

no image
Graph kernels for disease outcome prediction from protein-protein interaction networks

Borgwardt, KM., Vishwanathan, SVN., Schraudolph, N., Kriegel, H-P.

In pages: 4-15, (Editors: Altman, R.B. A.K. Dunker, L. Hunter, T. Murray, T.E. Klein), World Scientific, Hackensack, NJ, USA, Pacific Symposium on Biocomputing (PSB), January 2007 (inproceedings)

Abstract
It is widely believed that comparing discrepancies in the protein-protein interaction (PPI) networks of individuals will become an important tool in understanding and preventing diseases. Currently PPI networks for individuals are not available, but gene expression data is becoming easier to obtain and allows us to represent individuals by a co-integrated gene expression/protein interaction network. Two major problems hamper the application of graph kernels – state-of-the-art methods for whole-graph comparison – to compare PPI networks. First, these methods do not scale to graphs of the size of a PPI network. Second, missing edges in these interaction networks are biologically relevant for detecting discrepancies, yet, these methods do not take this into account. In this article we present graph kernels for biological network comparison that are fast to compute and take into account missing interactions. We evaluate their practical performance on two datasets of co-integrated gene expression/PPI networks.

ei

PDF [BibTex]

ei Borgwardt, KM., Vishwanathan, SVN., Schraudolph, N., Kriegel, H-P. Graph kernels for disease outcome prediction from protein-protein interaction networks In pages: 4-15, (Editors: Altman, R.B. A.K. Dunker, L. Hunter, T. Murray, T.E. Klein), World Scientific, Hackensack, NJ, USA, Pacific Symposium on Biocomputing (PSB), January 2007 (inproceedings)

PDF [BibTex]

no image
Some observations on the pedestal effect

Henning, G., Wichmann, F.

Journal of Vision, 7(1:3):1-15, January 2007 (article)

Abstract
The pedestal or dipper effect is the large improvement in the detectability of a sinusoidal grating observed when it is added to a masking or pedestal grating of the same spatial frequency, orientation, and phase. We measured the pedestal effect in both broadband and notched noiseVnoise from which a 1.5-octave band centered on the signal frequency had been removed. Although the pedestal effect persists in broadband noise, it almost disappears in the notched noise. Furthermore, the pedestal effect is substantial when either high- or low-pass masking noise is used. We conclude that the pedestal effect in the absence of notched noise results principally from the use of information derived from channels with peak sensitivities at spatial frequencies different from that of the signal and the pedestal. We speculate that the spatial-frequency components of the notched noise above and below the spatial frequency of the signal and the pedestal prevent ‘‘off-frequency looking,’’ that is, prevent the use of information about changes in contrast carried in channels tuned to spatial frequencies that are very much different from that of the signal and the pedestal. Thus, the pedestal or dipper effect measured without notched noise appears not to be a characteristic of individual spatial-frequency-tuned channels.

ei

PDF Web DOI [BibTex]

ei Henning, G., Wichmann, F. Some observations on the pedestal effect Journal of Vision, 7(1:3):1-15, January 2007 (article)

PDF Web DOI [BibTex]

no image
Cue Combination and the Effect of Horizontal Disparity and Perspective on Stereoacuity

Zalevski, AM., Henning, GB., Hill, NJ.

Spatial Vision, 20(1):107-138, January 2007 (article)

Abstract
Relative depth judgments of vertical lines based on horizontal disparity deteriorate enormously when the lines form part of closed configurations (Westheimer, 1979). In studies showing this effect, perspective was not manipulated and thus produced inconsistency between horizontal disparity and perspective. We show that stereoacuity improves dramatically when perspective and horizontal disparity are made consistent. Observers appear to use unhelpful perspective cues in judging the relative depth of the vertical sides of rectangles in a way not incompatible with a form of cue weighting. However, 95% confidence intervals for the weights derived for cues usually exceed the a-priori [0-1] range.

ei

PDF PDF DOI [BibTex]

ei Zalevski, AM., Henning, GB., Hill, NJ. Cue Combination and the Effect of Horizontal Disparity and Perspective on Stereoacuity Spatial Vision, 20(1):107-138, January 2007 (article)

PDF PDF DOI [BibTex]

no image
Independent Factor Reinforcement Learning for Portfolio Management

Li, J., Zhang, K., Chan, L.

In Proceedings of the 8th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2007), pages: 1020-1031, (Editors: H Yin and P Tiño and E Corchado and W Byrne and X Yao), Springer, Berlin, Germany, 8th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL), 2007 (inproceedings)

ei

Web [BibTex]

ei Li, J., Zhang, K., Chan, L. Independent Factor Reinforcement Learning for Portfolio Management In Proceedings of the 8th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2007), pages: 1020-1031, (Editors: H Yin and P Tiño and E Corchado and W Byrne and X Yao), Springer, Berlin, Germany, 8th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL), 2007 (inproceedings)

Web [BibTex]

no image
Classificazione di immagini telerilevate satellitari per agricoltura di precisione

Arnoldi, E., Bruzzone, L., Carlin, L., Pedron, L., Persello, C.

MondoGis: Il Mondo dei Sistemi Informativi Geografici, 63, pages: 13-17, 2007 (article)

ei

[BibTex]

ei Arnoldi, E., Bruzzone, L., Carlin, L., Pedron, L., Persello, C. Classificazione di immagini telerilevate satellitari per agricoltura di precisione MondoGis: Il Mondo dei Sistemi Informativi Geografici, 63, pages: 13-17, 2007 (article)

[BibTex]

no image
Separating convolutive mixtures by pairwise mutual information minimization", IEEE Signal Processing Letters

Zhang, K., Chan, L.

IEEE Signal Processing Letters, 14(12):992-995, 2007 (article)

Abstract
Blind separation of convolutive mixtures by minimizing the mutual information between output sequences can avoid the side effect of temporally whitening the outputs, but it involves the score function difference, whose estimation may be problematic when the data dimension is greater than two. This greatly limits the application of this method. Fortunately, for separating convolutive mixtures, pairwise independence of outputs leads to their mutual independence. As an implementation of this idea, we propose a way to separate convolutive mixtures by enforcing pairwise independence. This approach can be applied to separate convolutive mixtures of a moderate number of sources.

ei

Web [BibTex]

no image
Kernel-Based Nonlinear Independent Component Analysis

Zhang, K., Chan, L.

In Independent Component Analysis and Signal Separation, 7th International Conference, ICA 2007, pages: 301-308, (Editors: M E Davies and C J James and S A Abdallah and M D Plumbley), Springer, 7th International Conference on Independent Component Analysis and Signal Separation (ICA), 2007, Lecture Notes in Computer Science, Vol. 4666 (inproceedings)

ei

Web DOI [BibTex]

ei Zhang, K., Chan, L. Kernel-Based Nonlinear Independent Component Analysis In Independent Component Analysis and Signal Separation, 7th International Conference, ICA 2007, pages: 301-308, (Editors: M E Davies and C J James and S A Abdallah and M D Plumbley), Springer, 7th International Conference on Independent Component Analysis and Signal Separation (ICA), 2007, Lecture Notes in Computer Science, Vol. 4666 (inproceedings)

Web DOI [BibTex]

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.

am ei

PDF DOI [BibTex]

am ei Peters, J., Schaal, S., Schölkopf, B. Towards Machine Learning of Motor Skills In Proceedings of Autonome Mobile Systeme (AMS), pages: 138-144, (Editors: K Berns and T Luksch), 2007, clmc (inproceedings)

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.

am ei

[BibTex]

am ei Theodorou, E., Peters, J., Schaal, S. Reinforcement Learning for Optimal Control of Arm Movements In Abstracts of the 37st Meeting of the Society of Neuroscience., Neuroscience, 2007, clmc (inproceedings)

[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.

am ei

link (url) DOI [BibTex]

am ei Peters, J., Schaal, S. Reinforcement learning by reward-weighted regression for operational space control In Proceedings of the 24th Annual International Conference on Machine Learning, pages: 745-750, ICML, 2007, clmc (inproceedings)

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.

am ei

[BibTex]

am ei Peters, J., Theodorou, E., Schaal, S. Policy gradient methods for machine learning In Proceedings of the 14th INFORMS Conference of the Applied Probability Society, pages: 97-98, Eindhoven, Netherlands, July 9-11, 2007, 2007, clmc (inproceedings)

[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.

am ei

PDF DOI [BibTex]

am ei Peters, J., Schaal, S. Policy Learning for Motor Skills 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)

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.

am ei

link (url) DOI [BibTex]

am ei Peters, J., Schaal, S. Reinforcement learning for operational space control In Proceedings of the 2007 IEEE International Conference on Robotics and Automation, pages: 2111-2116, IEEE Computer Society, ICRA, 2007, clmc (inproceedings)

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.

am ei

link (url) DOI [BibTex]

am ei Peters, J., Schaal, S. Using reward-weighted regression for reinforcement learning of task space control 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)

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.

am ei

PDF [BibTex]

am ei Riedmiller, M., Peters, J., Schaal, S. Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pages: 254-261, ADPRL, 2007, clmc (inproceedings)

PDF [BibTex]

no image
Hand placement during quadruped locomotion in a humanoid robot: A dynamical system approach

Degallier, S., Righetti, L., Ijspeert, A.

In 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 2047-2052, IEEE, San Diego, USA, 2007 (inproceedings)

Abstract
Locomotion on an irregular surface is a challenging task in robotics. Among different problems to solve to obtain robust locomotion, visually guided locomotion and accurate foot placement are of crucial importance. Robust controllers able to adapt to sensory-motor feedbacks, in particular to properly place feet on specific locations, are thus needed. Dynamical systems are well suited for this task as any online modification of the parameters leads to a smooth adaptation of the trajectories, allowing a safe integration of sensory-motor feedback. In this contribution, as a first step in the direction of locomotion on irregular surfaces, we present a controller that allows hand placement during crawling in a simulated humanoid robot. The goal of the controller is to superimpose rhythmic movements for crawling with discrete (i.e. short-term) modulations of the hand placements to reach specific marks on the ground.

mg

link (url) DOI [BibTex]

mg Degallier, S., Righetti, L., Ijspeert, A. Hand placement during quadruped locomotion in a humanoid robot: A dynamical system approach In 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 2047-2052, IEEE, San Diego, USA, 2007 (inproceedings)

link (url) DOI [BibTex]

no image
Lower body realization of the baby humanoid - ‘iCub’

Tsagarakis, N., Becchi, F., Righetti, L., Ijspeert, A., Caldwell, D.

In 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 3616-3622, IEEE, San Diego, USA, 2007 (inproceedings)

Abstract
Nowadays, the understanding of the human cognition and it application to robotic systems forms a great challenge of research. The iCub is a robotic platform that was developed within the RobotCub European project to provide the cognition research community with an open baby- humanoid platform for understanding and development of cognitive systems. In this paper we present the design requirements and mechanical realization of the lower body developed for the "iCub". In particular the leg and the waist mechanisms adopted for lower body to match the size and physical abilities of a 2 frac12 year old human baby are introduced.

mg

link (url) DOI [BibTex]

mg Tsagarakis, N., Becchi, F., Righetti, L., Ijspeert, A., Caldwell, D. Lower body realization of the baby humanoid - ‘iCub’ In 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 3616-3622, IEEE, San Diego, USA, 2007 (inproceedings)

link (url) DOI [BibTex]

no image
iCub - The Design and Realization of an Open Humanoid Platform for Cognitive and Neuroscience Research

Tsagarakis, N., Metta, G., Sandini, G., Vernon, D., Beira, R., Becchi, F., Righetti, L., Santos-Victor, J., Ijspeert, A., Carrozza, M., Caldwell, D.

Advanced Robotics, 21(10):1151-1175, 2007 (article)

Abstract
The development of robotic cognition and the advancement of understanding of human cognition form two of the current greatest challenges in robotics and neuroscience, respectively. The RobotCub project aims to develop an embodied robotic child (iCub) with the physical (height 90 cm and mass less than 23 kg) and ultimately cognitive abilities of a 2.5-year-old human child. The iCub will be a freely available open system which can be used by scientists in all cognate disciplines from developmental psychology to epigenetic robotics to enhance understanding of cognitive systems through the study of cognitive development. The iCub will be open both in software, but more importantly in all aspects of the hardware and mechanical design. In this paper the design of the mechanisms and structures forming the basic 'body' of the iCub are described. The papers considers kinematic structures dynamic design criteria, actuator specification and selection, and detailed mechanical and electronic design. The paper concludes with tests of the performance of sample joints, and comparison of these results with the design requirements and simulation projects.

mg

link (url) DOI [BibTex]

mg Tsagarakis, N., Metta, G., Sandini, G., Vernon, D., Beira, R., Becchi, F., Righetti, L., Santos-Victor, J., Ijspeert, A., Carrozza, M., Caldwell, D. iCub - The Design and Realization of an Open Humanoid Platform for Cognitive and Neuroscience Research Advanced Robotics, 21(10):1151-1175, 2007 (article)

link (url) DOI [BibTex]