Sciweavers

6 search results - page 1 / 2
» Postponed Updates for Temporal-Difference Reinforcement Lear...
Sort
View
ISDA
2009
IEEE
15 years 4 months ago
Postponed Updates for Temporal-Difference Reinforcement Learning
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
Harm van Seijen, Shimon Whiteson
ICML
1999
IEEE
15 years 11 months ago
Least-Squares Temporal Difference Learning
Excerpted from: Boyan, Justin. Learning Evaluation Functions for Global Optimization. Ph.D. thesis, Carnegie Mellon University, August 1998. (Available as Technical Report CMU-CS-...
Justin A. Boyan
NIPS
2007
14 years 11 months ago
Incremental Natural Actor-Critic Algorithms
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...
JMLR
2010
119views more  JMLR 2010»
14 years 5 months ago
A Convergent Online Single Time Scale Actor Critic Algorithm
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their gen...
Dotan Di Castro, Ron Meir
78
Voted
JMLR
2006
153views more  JMLR 2006»
14 years 10 months ago
Collaborative Multiagent Reinforcement Learning by Payoff Propagation
In this article we describe a set of scalable techniques for learning the behavior of a group of agents in a collaborative multiagent setting. As a basis we use the framework of c...
Jelle R. Kok, Nikos A. Vlassis