Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
arXiv:2010.11655
Abstract
We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language. While different methods have been developed to represent the environment information and language actions, existing RL agents are not empowered with any reasoning capabilities to deal with textual games. In this work, we aim to conduct explicit reasoning with knowledge graphs for decision making, so that the actions of an agent are generated and supported by an interpretable inference procedure. We propose a stacked hierarchical attention mechanism to construct an explicit representation of the reasoning process by exploiting the structure of the knowledge graph. We extensively evaluate our method on a number of man-made benchmark games, and the experimental results demonstrate that our method performs better than existing text-based agents.
Accepted by NeurIPS2020
References in corpus (14)
- Playing Atari with Deep Reinforcement Learning
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
- Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
- Variational Reasoning for Question Answering with Knowledge Graph
- Visualizing and Understanding Atari Agents
- Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
- Counting to Explore and Generalize in Text-based Games
- Graph Constrained Reinforcement Learning for Natural Language Action Spaces
- NAIL: A General Interactive Fiction Agent
- Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
- Building Dynamic Knowledge Graphs from Text-based Games
- Reasoning and Generalization in RL: A Tool Use Perspective
- Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning