38 search results - page 5 / 8 » On the Convergence of Optimistic Policy Iteration |
CORR
2006
Springer
13 years 7 months ago
2006
Springer
This paper addresses the issue of policy evaluation in Markov Decision Processes, using linear function approximation. It provides a unified view of algorithms such as TD(), LSTD()...
CDC
2010
IEEE
13 years 2 months ago
2010
IEEE
Approximate policy iteration methods based on temporal differences are popular in practice, and have been tested extensively, dating to the early nineties, but the associated conve...
ICONIP
2009
13 years 5 months ago
2009
Reinforcement learning induces non-stationarity at several levels. Adaptation to non-stationary environments is of course a desired feature of a fair RL algorithm. Yet, even if the...
CORR
2011
Springer
13 years 2 months ago
2011
Springer
—We propose a dynamic spectrum access scheme where secondary users recommend “good” channels to each other and access accordingly. We formulate the problem as an average rewa...
NIPS
2007
13 years 8 months ago
2007
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...