495 search results - page 3 / 99 » Constructing States for Reinforcement Learning |
ICML
2005
IEEE
14 years 6 months ago
2005
IEEE
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...
ILP
2007
Springer
13 years 11 months ago
2007
Springer
Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...
ECAI
2006
Springer
13 years 8 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...
ICML
2003
IEEE
14 years 6 months ago
2003
IEEE
We present metric?? , a provably near-optimal algorithm for reinforcement learning in Markov decision processes in which there is a natural metric on the state space that allows t...
NCI
2004
13 years 6 months ago
2004
This paper describes a method for hierarchical reinforcement learning in which high-level policies automatically discover subgoals, and low-level policies learn to specialize for ...