16 search results - page 1 / 4 » On Average Versus Discounted Reward Temporal-Difference Lear... |
ML
2002
ACM
13 years 7 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...
ALT
2006
Springer
14 years 4 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
1996
IEEE
14 years 8 months ago
1996
IEEE
Research in reinforcementlearning (RL)has thus far concentrated on two optimality criteria: the discounted framework, which has been very well-studied, and the averagereward frame...
CIG
2006
IEEE
14 years 1 months ago
2006
IEEE
Abstract— This paper compares the use of temporal difference learning (TDL) versus co-evolutionary learning (CEL) for acquiring position evaluation functions for the game of Othe...
ICML
2001
IEEE
14 years 8 months ago
2001
IEEE
Hierarchical reinforcement learning (RL) is a general framework which studies how to exploit the structure of actions and tasks to accelerate policy learning in large domains. Pri...