ML
2002
ACM
13 years 4 months ago
2002
ACM
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
IJCAI
2001
13 years 6 months ago
2001
A general and expressive model of sequential decision making under uncertainty is provided by the Markov decision processes (MDPs) framework. Complex applications with very large ...
COLT
2003
Springer
13 years 10 months ago
2003
Springer
We study on-line play of repeated matrix games in which the observations of past actions of the other player and the obtained reward are partial and stochastic. We define the Part...
COLT
2007
Springer
13 years 11 months ago
2007
Springer
Bounded parameter Markov Decision Processes (BMDPs) address the issue of dealing with uncertainty in the parameters of a Markov Decision Process (MDP). Unlike the case of an MDP, t...
ALT
2006
Springer
14 years 1 months ago
2006
Springer
Consider an agent interacting with an environment in cycles. In every interaction cycle the agent is rewarded for its performance. We compare the average reward U from cycle 1 to ...
ICML
2000
IEEE
14 years 5 months ago
2000
IEEE
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...