Sciweavers

1233 search results - page 67 / 247
» Feudal Reinforcement Learning
Sort
View
ICAART
2010
INSTICC
14 years 5 months ago
A Cautious Approach to Generalization in Reinforcement Learning
Raphael Fonteneau, Susan A. Murphy, Louis Wehenkel...
ISDA
2009
IEEE
14 years 2 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
ATAL
2009
Springer
14 years 2 months ago
Transferring experience in reinforcement learning through task decomposition
Ioannis Partalas, Grigorios Tsoumakas, Konstantino...