343 search results - page 1 / 69 » Action discovery for reinforcement learning |
NIPS
1994
13 years 6 months ago
1994
Reinforcement learning addresses the problem of learning to select actions in order to maximize one's performance inunknownenvironments. Toscale reinforcement learning to com...
ATAL
2010
Springer
13 years 6 months ago
2010
Springer
ECAI
2006
Springer
13 years 9 months ago
2006
Springer
Abstract. This paper proposes a novel approach to discover options in the form of conditionally terminating sequences, and shows how they can be integrated into reinforcement learn...
ECML
2003
Springer
13 years 10 months ago
2003
Springer
We present in this paper a method to introduce a priori knowledge into reinforcement learning using temporally extended actions. The aim of our work is to reduce the learning time ...
ICML
2008
IEEE
14 years 6 months ago
2008
IEEE
We present an algorithm, HI-MAT (Hierarchy Induction via Models And Trajectories), that discovers MAXQ task hierarchies by applying dynamic Bayesian network models to a successful...