Generalization in Text-based Games via Hierarchical Reinforcement Learning
arXiv:2109.09968
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.
41 pages, 11 figures, EMNLP2021 Findings
References in corpus (9)
- FeUdal Networks for Hierarchical Reinforcement Learning
- Why We Need New Evaluation Metrics for NLG
- Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
- From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
- Graph Constrained Reinforcement Learning for Natural Language Action Spaces
- NAIL: A General Interactive Fiction Agent
- BeBold: Exploration Beyond the Boundary of Explored Regions
- Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
- How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents