3084 search results - page 136 / 617 » Learning to Take Actions |
COLT
2004
Springer
15 years 3 months ago
2004
Springer
Abstract. We provide a natural learning process in which the joint frequency of empirical play converges into the set of convex combinations of Nash equilibria. In this process, al...
ISAMI
2010
14 years 8 months ago
2010
Intelligent Environments are supposed to act proactively anticipating user's needs and preferences in order to provide effective support. Therefore, learning user's frequ...
COLT
2004
Springer
15 years 3 months ago
2004
Springer
Abstract. We consider Reinforcement Learning for average reward zerosum stochastic games. We present and analyze two algorithms. The first is based on relative Q-learning and the ...
ICANN
2001
Springer
15 years 2 months ago
2001
Springer
Unlike traditional reinforcement learning (RL), market-based RL is in principle applicable to worlds described by partially observable Markov Decision Processes (POMDPs), where an ...
ACL
2008
14 years 11 months ago
2008
We use an EM algorithm to learn user models in a spoken dialog system. Our method requires automatically transcribed (with ASR) dialog corpora, plus a model of transcription error...