We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...
Relational reinforcement learning (RRL) is a Q-learning technique which uses first order regression techniques to generalize the Qfunction. Both the relational setting and the Q-l...
In this paper we describe a context-sensitive way to change an active mobile phone profile. We present a method to create a proactive and adaptive phone profile control system that...
Abstract. Learning to act in an unknown partially observable domain is a difficult variant of the reinforcement learning paradigm. Research in the area has focused on model-free m...