139 search results - page 26 / 28 » Model-based function approximation in reinforcement learning |
136
click to vote
JMLR
2010
14 years 8 months ago
2010
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...
119
Voted
ICML
2009
IEEE
16 years 2 months ago
2009
IEEE
We consider the task of reinforcement learning with linear value function approximation. Temporal difference algorithms, and in particular the Least-Squares Temporal Difference (L...
115
click to vote
ECAI
2006
Springer
15 years 5 months ago
2006
Springer
Abstract. We formulate the problem of least squares temporal difference learning (LSTD) in the framework of least squares SVM (LS-SVM). To cope with the large amount (and possible ...
116
Voted
ICML
2009
IEEE
15 years 8 months ago
2009
IEEE
Virtually all methods of learning dynamic systems from data start from the same basic assumption: that the learning algorithm will be provided with a sequence, or trajectory, of d...
136
click to vote
NIPS
2001
15 years 3 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...