64 search results - page 7 / 13 » Multi-Agent Learning with Policy Prediction |
RSS
2007
14 years 9 days ago
2007
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
NIPS
2001
14 years 8 days 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. ...
UM
2005
Springer
14 years 4 months ago
2005
Springer
Inference and decision making with probabilistic user models may be infeasible on portable devices such as cell phones. We highlight the opportunity for storing and using precomput...
IWLCS
2005
Springer
14 years 4 months ago
2005
Springer
Aiming to clarify the convergence or divergence conditions for Learning Classifier System (LCS), this paper explores: (1) an extreme condition where the reinforcement process of ...
ATAL
2010
Springer
14 years 8 hour ago
2010
Springer
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...