Generalization in Text-based Games via Hierarchical Reinforcement Learning
Xu, Yunqiu, Fang, Meng, Chen, Ling, Du, Yali, Zhang, Chengqi
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Sep-21-2021
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- Europe
- United Kingdom > England
- Greater London > London (0.04)
- Netherlands > North Brabant
- Eindhoven (0.04)
- United Kingdom > England
- Oceania > Australia
- Genre:
- Research Report (1.00)
- Industry:
- Leisure & Entertainment > Games (1.00)