69 search results - page 8 / 14 » PAC-Bayesian Policy Evaluation for Reinforcement Learning |
ICAC
2009
IEEE
13 years 4 months ago
2009
IEEE
Distributed W-Learning (DWL) is a reinforcement learningbased algorithm for multi-policy optimization in agent-based systems. In this poster we propose the use of DWL for decentra...
ECML
2007
Springer
14 years 26 days ago
2007
Springer
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
ICML
2001
IEEE
14 years 7 months ago
2001
IEEE
Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maxi...
BERTINORO
2005
Springer
14 years 7 days ago
2005
Springer
Abstract. This paper describes the application of a decentralised coordination algorithm, called Collaborative Reinforcement Learning (CRL), to two different distributed system pr...
AAAI
2007
13 years 9 months ago
2007
In this paper we present RETALIATE, an online reinforcement learning algorithm for developing winning policies in team firstperson shooter games. RETALIATE has three crucial chara...