215 search results - page 19 / 43 » Model-Based Reinforcement Learning with Continuous States an... |
105
click to vote
Publication
Abstract: Several approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervis...
NIPS
1996
15 years 29 days ago
1996
Closed-loop control relies on sensory feedback that is usually assumed to be free. But if sensing incurs a cost, it may be coste ective to take sequences of actions in open-loop m...
ICML
2005
IEEE
16 years 13 days ago
2005
IEEE
We prove a quantitative connection between the expected sum of rewards of a policy and binary classification performance on created subproblems. This connection holds without any ...
110
click to vote
GECCO
2007
Springer
15 years 5 months ago
2007
Springer
Wilson introduced XCSF as a successor to XCS. The major development of XCSF is the concept of a computed prediction. The efficiency of XCSF in dealing with numerical input and con...
JUCS
2007
14 years 11 months ago
2007
Abstract: Classification-based reinforcement learning (RL) methods have recently been proposed as an alternative to the traditional value-function based methods. These methods use...