Sciweavers

ML
2002
ACM
168views Machine Learning» more  ML 2002»
14 years 3 days ago
On Average Versus Discounted Reward Temporal-Difference Learning
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
John N. Tsitsiklis, Benjamin Van Roy
IJCAI
2001
14 years 1 months ago
Complexity of Probabilistic Planning under Average Rewards
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 ...
Jussi Rintanen
COLT
2003
Springer
14 years 5 months ago
On-Line Learning with Imperfect Monitoring
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...
Shie Mannor, Nahum Shimkin
COLT
2007
Springer
14 years 6 months ago
Bounded Parameter Markov Decision Processes with Average Reward Criterion
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...
Ambuj Tewari, Peter L. Bartlett
ALT
2006
Springer
14 years 9 months ago
General Discounting Versus Average Reward
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 ...
Marcus Hutter
ICML
2000
IEEE
15 years 1 months ago
Reinforcement Learning in POMDP's via Direct Gradient Ascent
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
Jonathan Baxter, Peter L. Bartlett