Generalization in Text-based Games via Hierarchical Reinforcement Learning
This addresses the problem of poor generalization in text-based game agents for AI researchers, though it appears incremental as it builds on existing knowledge graph-based RL methods.
The paper tackles the challenge of generalization in text-based games by introducing a hierarchical reinforcement learning framework that decomposes games into subtasks and uses goal-conditioned learning, showing favorable generalizability across various difficulty levels.
Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents. However, the generalization still remains a big challenge as the agents depend critically on the complexity and variety of training tasks. In this paper, we address this problem by introducing a hierarchical framework built upon the knowledge graph-based RL agent. In the high level, a meta-policy is executed to decompose the whole game into a set of subtasks specified by textual goals, and select one of them based on the KG. Then a sub-policy in the low level is executed to conduct goal-conditioned reinforcement learning. We carry out experiments on games with various difficulty levels and show that the proposed method enjoys favorable generalizability.