Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement LearningDownload PDF


Sep 29, 2021 (edited Oct 06, 2021)ICLR 2022 Conference Blind SubmissionReaders: Everyone
  • Keywords: Interpretable Reinforcement Learning, Generalization, Robustness
  • Abstract: We present a two-step hybrid reinforcement learning (RL) policy that is designed to generate interpretable and robust hierarchical policies on the RL problem with graph-based input. Unlike prior deep reinforcement learning policies parameterized by an end-to-end black-box graph neural network, our approach disentangles the decision-making process into two steps. The first step is a simplified classification problem that maps the graph input to an action group where all actions share a similar semantic meaning. The second step implements a sophisticated rule-miner that conduct explicit one-hop reasoning over the graph and identifies decisive edges in the graph input without the necessity of heavy domain knowledge. This two-step hybrid policy presents human-friendly interpretations and achieves better performance in terms of generalization and robustness. Extensive experimental studies on four levels of complex text-based games have demonstrated the superiority of the proposed method compared to the state-of-the-art.
  • One-sentence Summary: A two-step hybrid policy designed for graph-based interpretable reinforcement learning.
0 Replies