6 search results - page 1 / 2 » PAC model-free reinforcement learning |
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...
NIPS
2001
13 years 5 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We propose a model-based learning algorithm, the Adaptive Aggregation Algorithm (AAA), that aims to solve the online, continuous state space reinforcement learning problem in a de...
ESANN
2008
13 years 5 months ago
2008
The aim of this paper is to enhance the performance of a reinforcement learning game agent controller, within a dynamic game environment, through the retention of learned informati...
JMLR
2010
12 years 11 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...