190 search results - page 3 / 38 » Abstraction and Generalization in Reinforcement Learning: A ... |
ATAL
2006
Springer
13 years 10 months ago
2006
Springer
RVRL (Rule Value Reinforcement Learning) is a new algorithm which extends an existing learning framework that models the environment of a situated agent using a probabilistic rule...
CLA
2007
13 years 7 months ago
2007
The generalization of policies in reinforcement learning is a main issue, both from the theoretical model point of view and for their applicability. However, generalizing from a se...
ECML
2004
Springer
13 years 11 months ago
2004
Springer
Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....
ICML
2000
IEEE
14 years 7 months ago
2000
IEEE
Stochastic games are a generalization of MDPs to multiple agents, and can be used as a framework for investigating multiagent learning. Hu and Wellman (1998) recently proposed a m...
JMLR
2010
13 years 1 months ago
2010
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...