English

Generalization in Text-based Games via Hierarchical Reinforcement Learning

Computation and Language 2021-09-22 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2109.09968,
  title  = {Generalization in Text-based Games via Hierarchical Reinforcement Learning},
  author = {Yunqiu Xu and Meng Fang and Ling Chen and Yali Du and Chengqi Zhang},
  journal= {arXiv preprint arXiv:2109.09968},
  year   = {2021}
}

Comments

41 pages, 11 figures, EMNLP2021 Findings

R2 v1 2026-06-24T06:10:10.892Z