意味的ゴールを用いた解釈可能な階層型エージェントフレームワーク
Towards an Interpretable Hierarchical Agent Framework using Semantic Goals
計画と意味的ゴール指向強化学習を組み合わせ、空間・触覚述語から解釈可能なゴール空間を構築することで、長期的タスクを効率的に学習する階層型エージェントを提案した。
著者: Bharat Prakash, Nicholas Waytowich, Tim Oates, Tinoosh Mohsenin
分類: cs.LG, cs.RO
原文アブストラクト
Learning to solve long horizon temporally extended tasks with reinforcement learning has been a challenge for several years now. We believe that it is important to leverage both the hierarchical structure of complex tasks and to use expert supervision whenever possible to solve such tasks. This work introduces an interpretable hierarchical agent framework by combining planning and semantic goal directed reinforcement learning. We assume access to certain spatial and haptic predicates and construct a simple and powerful semantic goal space. These semantic goal representations are more interpretable, making expert supervision and intervention easier. They also eliminate the need to write complex, dense reward functions thereby reducing human engineering effort. We evaluate our framework on a robotic block manipulation task and show that it performs better than other methods, including both sparse and dense reward functions. We also suggest some next steps and discuss how this framework makes interaction and collaboration with humans easier.
