ECML 2005 - PDF Preprint Papers

ECML 2005 European Working Session on Learning

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ECML-2005 Paper

click to vote

ECML
2005
Springer

193views Machine Learning» more ECML 2005»

Natural Actor-Critic

14 years 5 months ago

Download www-clmc.usc.edu

This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari...

Jan Peters, Sethu Vijayakumar, Stefan Schaal

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status

1	193	Natural Actor-Critic	claim
2	168	A Model Based Method for Automatic Facial Expression Recognition	claim
3	154	U-Likelihood and U-Updating Algorithms: Statistical Inference in Latent Variable Models	claim
4	147	Combining Bias and Variance Reduction Techniques for Regression Trees	claim
5	145	Fitting the Smallest Enclosing Bregman Ball	claim
6	143	Active Learning in Partially Observable Markov Decision Processes	claim
7	129	Bayesian Network Learning with Abstraction Hierarchies and Context-Specific Independence	claim
8	124	Thwarting the Nigritude Ultramarine: Learning to Identify Link Spam	claim
9	124	Active Learning for Probability Estimation Using Jensen-Shannon Divergence	claim
10	124	On Discriminative Joint Density Modeling	claim
11	121	Fast Non-negative Dimensionality Reduction for Protein Fold Recognition	claim
12	120	Using Rewards for Belief State Updates in Partially Observable Markov Decision Processes	claim
13	119	Estimation of Mixture Models Using Co-EM	claim
14	115	Nonrigid Embeddings for Dimensionality Reduction	claim
15	114	Multi-view Discriminative Sequential Learning	claim
16	112	Margin-Sparsity Trade-Off for the Set Covering Machine	claim
17	110	Counting Positives Accurately Despite Inaccurate Classification	claim
18	108	A Distance-Based Approach for Action Recommendation	claim
19	106	Simple Test Strategies for Cost-Sensitive Decision Trees	claim
20	106	Annealed Discriminant Analysis	claim
21	106	Clustering and Metaclustering with Nonnegative Matrix Decompositions	claim
22	105	Multi-armed Bandit Algorithms and Empirical Evaluation	claim
23	103	A Comparison of Approaches for Learning Probability Trees	claim
24	102	Infinite Ensemble Learning with Support Vector Machines	claim
25	101	Model-Based Online Learning of POMDPs	claim
26	99	Learning to Complete Sentences	claim
27	98	Mode Directed Path Finding	claim
28	97	Inducing Hidden Markov Models to Model Long-Term Dependencies	claim
29	96	Learning from Positive and Unlabeled Examples with Different Data Distributions	claim
30	96	Severe Class Imbalance: Why Better Algorithms Aren't the Answer	claim
31	95	Towards Finite-Sample Convergence of Direct Reinforcement Learning	claim
32	95	Model Selection in Omnivariate Decision Trees	claim
33	94	Rotational Prior Knowledge for SVMs	claim
34	93	Kernel Basis Pursuit	claim
35	91	A SAT-Based Version Space Algorithm for Acquiring Constraint Satisfaction Problems	claim
36	87	Using Advice to Transfer Knowledge Acquired in One Reinforcement Learning Task to Another	claim
37	85	Machine Learning of Plan Robustness Knowledge About Instances	claim
38	84	On the LearnAbility of Abstraction Theories from Observations for Relational Learning	claim
39	83	A Similar Fragments Merging Approach to Learn Automata on Proteins	claim
40	80	Learning (k, l)-Contextual Tree Languages for Information Extraction	claim
41	77	Error-Sensitive Grading for Model Combination	claim
42	65	An Integrated Approach to Learning Bayesian Networks of Rules	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers