Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning
This addresses the issue of interpretability and generalization in textual reinforcement learning for AI agents, representing an incremental improvement over existing methods.
The paper tackles the problem of text-based reinforcement learning agents producing uninterpretable policies with poor generalization by proposing a neuro-symbolic agent that learns abstract interpretable rules, resulting in better generalization to unseen games and requiring fewer training interactions.
Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games. On the other hand, neuro-symbolic methods, specifically those that leverage an intermediate formal representation, are gaining significant attention in language understanding tasks. This is because of their advantages ranging from inherent interpretability, the lesser requirement of training data, and being generalizable in scenarios with unseen data. Therefore, in this paper, we propose a modular, NEuro-Symbolic Textual Agent (NESTA) that combines a generic semantic parser with a rule induction system to learn abstract interpretable rules as policies. Our experiments on established text-based game benchmarks show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better generalization to unseen test games and learning from fewer training interactions.