Search

2008

Lizotte, Daniel, Wang, Tao, Bowling, Michael, Schuurmans, Dale

Technical report TR08-16. We propose a dual approach to dynamic programming and reinforcement learning based on maintaining an explicit representation of visit distributions as opposed to value functions. An advantage of working in the dual is that it allows one to exploit techniques for...

2006

Wang, Tao, Schuurmans, Dale, Bowling, Michael

Technical report TR06-26. We investigate the dual approach to dynamic programming and reinforcement learning, based on maintaining an explicit representation of stationary distributions as opposed to value functions. A significant advantage of the dual approach is that it allows one to exploit...

2007

Li, Lihong

Technical report TR07-12. One key topic in reinforcement learning is function approximation which is critical for the success of reinforcement learning in domains with large state spaces. Unfortunately, function approximation can lead to several problems including the suboptimality of the...

2011

Yao, Hengshuai

Technical report TR11-04. World model is very important for model-based reinforcement learning. For example, a model is frequently used in Dyna: in learning steps to select actions and in planning steps to project sampled states or features. In this paper we propose least-squares Dyna (LS-Dyna)...

2007

Wang, Tao, Schuurmans, Dale, Bowling, Michael, Lizotte, Daniel

Technical report TR07-05. We investigate novel, dual algorithms for dynamic programming and reinforcement learning, based on maintaining explicit representations of stationary distributions instead of value functions. In particular, we investigate the convergence properties of standard dynamic...