Sub-policy Adaptation for Hierarchical Reinforcement LearningDownload PDF


May 16, 2019 (edited Jun 14, 2019)ICML 2019 Workshop AMTL Blind SubmissionReaders: Everyone
  • Keywords: Hierarchical Reinforcement Learning, Transfer, Skill Discovery
  • Abstract: Hierarchical Reinforcement Learning is a promising approach to long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Treating the skills as fixed can lead to significant sub-optimality in the transfer setting. In this work, we propose a novel algorithm to discover a set of skills, and continuously adapt them along with the higher level even when training on a new task. Our main contributions are two-fold. First, we derive a new hierarchical policy gradient, as well as an unbiased latent-dependent baseline. We introduce Hierarchical Proximal Policy Optimization (HiPPO), an on-policy method to efficiently train all levels of the hierarchy simultaneously. Second, we propose a method of training time-abstractions that improves the robustness of the obtained skills to environment changes. Code and results are available at
  • TL;DR: We propose HiPPO, a stable Hierarchical Reinforcement Learning algorithm that can train several levels of the hierarchy simultaneously, giving good performance both in skill discovery and adaptation.
0 Replies