Batch policy iteration algorithms for continuous domains

This paper establishes the link between an adaptation of the policy iteration method for Markov decision processes with continuous state and action spaces and the policy gradient method when the differentiation of the mean value is directly done over the policy without parameterization. This approach allows deriving sound and practical batch Reinforcement Learning algorithms for continuous state and action spaces.

Authors

• Bilal Piot
• Matthieu Geist Google DeepMind
• Olivier Pietquin Cohere

Keywords

No keywords are indexed for this paper.