GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms - researchr publication

researchr

You are not signed in
Sign in
Sign up

Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer. GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. In Olivier Buffet, Alain Dutech, Vincent Thomas, editors, Journées Francophone Planification, Décision et Apprentissage pour la conduite des systèmes, JFPDA 2018, Nancy, France, July 2-3, 2018. HAL, 2018. [doi]

Abstract is missing.

runs on WebDSL