Reinforcement learning with rare significant events: direct policy search vs. gradient policy search

Paul Ecoffet, Nicolas Fontbonne, Jean-Baptiste André, Nicolas Bredèche. Reinforcement learning with rare significant events: direct policy search vs. gradient policy search. In Krzysztof Krawiec, editor, GECCO '21: Genetic and Evolutionary Computation Conference, Companion Volume, Lille, France, July 10-14, 2021. pages 97-98, ACM, 2021. [doi]

Abstract

Abstract is missing.