199 search results - page 1 / 40 » Efficient Reinforcement Learning with Relocatable Action Mod... |
AAAI
2007
13 years 6 months ago
2007
EWRL
2008
13 years 6 months ago
2008
We consider reinforcement learning in the parameterized setup, where the model is known to belong to a parameterized family of Markov Decision Processes (MDPs). We further impose ...
SAC
2005
ACM
13 years 9 months ago
2005
ACM
This paper presents a novel model of reinforcement learning agents. A feature of our learning agent model is to integrate analytic hierarchy process (AHP) into a standard reinforc...
BROADNETS
2004
IEEE
13 years 8 months ago
2004
IEEE
The scarcity and large fluctuations of link bandwidth in wireless networks have motivated the development of adaptive multimedia services in mobile communication networks, where i...
ICML
2006
IEEE
14 years 5 months ago
2006
IEEE
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...