Sciweavers

COLT
1994
Springer

Efficient Reinforcement Learning

13 years 7 months ago
Efficient Reinforcement Learning
Realistic domains for learning possess regularities that make it possible to generalize experience across related states. This paper explores an environment-modeling framework that represents transitions as state-independent outcomes that are common to all states that share the same type. We analyze a set of novel learning problems that arise in this framework, providing lower and upper bounds. We single out one particular variant of practical interest and provide an efficient algorithm and experimental results in both simulated and robotic environments.
Claude-Nicolas Fiechter
Added 09 Aug 2010
Updated 09 Aug 2010
Type Conference
Year 1994
Where COLT
Authors Claude-Nicolas Fiechter
Comments (0)