Publication
Self-paced contextual reinforcement learning
Pascal Klink; Hany Abdulsamad; Boris Belousov; Jan Peters
In: Leslie Pack Kaelbling; Danica Kragic; Komei Sugiura (Hrsg.). 3rd Annual Conference on Robot Learning. Conference on Robot Learning (CoRL-2019), October 30 - November 1, Osaka, Japan, Pages 513-529, Proceedings of Machine Learning Research (PMLR), Vol. 100, PMLR, 2019.
Abstract
Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of behaviors across related tasks, it generally relies on uninformed sampling of environments from an unknown, uncontrolled context distribution, thus missing the benefits of structured, sequential learning. We introduce a novel relative entropy reinforcement learning algorithm that gives the agent the freedom to control the intermediate task distribution, allowing for its gradual progression towards the target context distribution. Empirical evaluation shows that the proposed curriculum learning scheme drastically improves sample efficiency and enables learning in scenarios with both broad and sharp target context distributions in which classical approaches perform sub-optimally.