Sciweavers

267 search results - page 28 / 54
» The Dynamics of Multi-Agent Reinforcement Learning
Sort
View
AAAI
1998
14 years 11 months ago
Applying Online Search Techniques to Continuous-State Reinforcement Learning
In this paper, we describe methods for e ciently computing better solutions to control problems in continuous state spaces. We provide algorithms that exploit online search to boo...
Scott Davies, Andrew Y. Ng, Andrew W. Moore
PKDD
2010
Springer
129views Data Mining» more  PKDD 2010»
14 years 8 months ago
Smarter Sampling in Model-Based Bayesian Reinforcement Learning
Abstract. Bayesian reinforcement learning (RL) is aimed at making more efficient use of data samples, but typically uses significantly more computation. For discrete Markov Decis...
Pablo Samuel Castro, Doina Precup
NIPS
1996
14 years 11 months ago
Exploiting Model Uncertainty Estimates for Safe Dynamic Control Learning
Model learning combined with dynamic programming has been shown to be e ective for learning control of continuous state dynamic systems. The simplest method assumes the learned mod...
Jeff G. Schneider
IROS
2006
IEEE
187views Robotics» more  IROS 2006»
15 years 3 months ago
Fast and Stable Learning of Quasi-Passive Dynamic Walking by an Unstable Biped Robot based on Off-Policy Natural Actor-Critic
— Recently, many researchers on humanoid robotics are interested in Quasi-Passive-Dynamic Walking (Quasi-PDW) which is similar to human walking. It is desirable that control para...
Tsuyoshi Ueno, Yutaka Nakamura, Takashi Takuma, To...
ECML
2007
Springer
14 years 11 months ago
Sequence Labeling with Reinforcement Learning and Ranking Algorithms
Many problems in areas such as Natural Language Processing, Information Retrieval, or Bioinformatic involve the generic task of sequence labeling. In many cases, the aim is to assi...
Francis Maes, Ludovic Denoyer, Patrick Gallinari