Sciweavers

1235 search results - page 115 / 247
» ABC Reinforcement Learning
Sort
View
ICAART
2010
INSTICC
16 years 4 days ago
A Cautious Approach to Generalization in Reinforcement Learning
Raphael Fonteneau, Susan A. Murphy, Louis Wehenkel...
ISDA
2009
IEEE
15 years 9 months ago
Postponed Updates for Temporal-Difference Reinforcement Learning
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 ...
Harm van Seijen, Shimon Whiteson