Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning
This work addresses the need for interpretable reinforcement learning policies in domains like text-based games, offering a novel approach that improves robustness and generalization, though it is incremental in its hybrid design.
The paper tackles the problem of generating interpretable and robust hierarchical policies in graph-based reinforcement learning by proposing a two-step hybrid policy that disentangles decision-making into action grouping and explicit graph reasoning, achieving better performance and generalization compared to state-of-the-art methods on complex text-based games.
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 conducts 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.