ACCEPTED PAPERS

Each individual paper may be downloaded by clicking on its title. Alternatively, you can download the proceedings as a single file.

 Improving Bayesian reinforcement learning using transition abstraction
 Daniel Acuna and Paul Schrater

 Manifold embeddings for model-based reinforcement learning of neurostimulation policies
 Keith Bush, Joelle Pineau and Massimo Avoli

 Situation dependent spatial abstraction in reinforcement learning based on structural knowledge
 Lutz Frommberger

 An empirical comparison of abstraction in models of Markov decision processes
 Todd Hester and Peter Stone

 Automated discovery of options in factored reinforcement learning
 Olga Kozlova, Olivier Sigaud and Christophe Meyer

 Hierarchical skill learning for high-level planning
 James MacGlashan and Marie desJardins

 Basis function construction for hierarchical reinforcement learning
 Sarah Osentoski and Sridhar Mahadevan

 Towards feature selection in actor-critic algorithms
 Khashayar Rohanimanesh, Nicholas Roy and Russ Tedrake

 Finding equivalences among abstract actions
 Alicia Peregrin Wolfe

 Dyna(k): A multi-step Dyna planning
 Hengshuai Yao, Rich Sutton, Shalabh Bhatnagar, Dongcui Diao and Csaba Szepesvári