Sciweavers

458 search results - page 7 / 92
» Q-Decomposition for Reinforcement Learning Agents
Sort
View
NIPS
2000
13 years 8 months ago
Programmable Reinforcement Learning Agents
We present an expressive agent design language for reinforcement learning that allows the user to constrain the policies considered by the learning process.The language includes s...
David Andre, Stuart J. Russell
AAAI
2007
13 years 9 months ago
Efficient Reinforcement Learning with Relocatable Action Models
Bethany R. Leffler, Michael L. Littman, Timothy Ed...
ATAL
2008
Springer
13 years 9 months ago
The utility of temporal abstraction in reinforcement learning
Nicholas K. Jong, Todd Hester, Peter Stone