Sciweavers

Share
6 search results - page 1 / 2
» PAC model-free reinforcement learning
Sort
View
ICML
2006
IEEE
12 years 6 months ago
PAC model-free reinforcement learning
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...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...
NIPS
2001
11 years 6 months ago
Model-Free Least-Squares Policy Iteration
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. ...
Michail G. Lagoudakis, Ronald Parr
COLT
2008
Springer
11 years 7 months ago
Adaptive Aggregation for Reinforcement Learning with Efficient Exploration: Deterministic Domains
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...
Andrey Bernstein, Nahum Shimkin
ESANN
2008
11 years 6 months ago
Improvement in Game Agent Control Using State-Action Value Scaling
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...
Leo Galway, Darryl Charles, Michaela M. Black
JMLR
2010
148views more  JMLR 2010»
11 years 7 days ago
A Generalized Path Integral Control Approach to Reinforcement Learning
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...
Evangelos Theodorou, Jonas Buchli, Stefan Schaal
books