EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning
This work addresses generalization issues in textual reinforcement learning for NLP tasks, offering a more interpretable and transferable approach, though it is incremental as it builds on existing neurosymbolic methods.
The paper tackles the challenge of generalization in text-based games by introducing EXPLORER, a neurosymbolic agent that combines neural exploration with symbolic exploitation, resulting in improved performance on both seen and unseen objects compared to baseline agents.
Text-based games (TBGs) have emerged as an important collection of NLP tasks, requiring reinforcement learning (RL) agents to combine natural language understanding with reasoning. A key challenge for agents attempting to solve such tasks is to generalize across multiple games and demonstrate good performance on both seen and unseen objects. Purely deep-RL-based approaches may perform well on seen objects; however, they fail to showcase the same performance on unseen objects. Commonsense-infused deep-RL agents may work better on unseen data; unfortunately, their policies are often not interpretable or easily transferable. To tackle these issues, in this paper, we present EXPLORER which is an exploration-guided reasoning agent for textual reinforcement learning. EXPLORER is neurosymbolic in nature, as it relies on a neural module for exploration and a symbolic module for exploitation. It can also learn generalized symbolic policies and perform well over unseen data. Our experiments show that EXPLORER outperforms the baseline agents on Text-World cooking (TW-Cooking) and Text-World Commonsense (TWC) games.