24 search results - page 3 / 5 » Technical Update: Least-Squares Temporal Difference Learning |
103
click to vote
ISDA
2009
IEEE
15 years 6 months ago
2009
IEEE
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
NIPS
2007
15 years 22 days ago
2007
COLT
2000
Springer
15 years 3 months ago
2000
Springer
We give the first rigorous upper bounds on the error of temporal difference (td) algorithms for policy evaluation as a function of the amount of experience. These upper bounds pr...
100
click to vote
AAAI
2011
13 years 11 months ago
2011
In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...
113
click to vote
JMLR
2010
14 years 6 months ago
2010
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their gen...