Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
arXiv:2005.00811
Abstract
In this paper, we consider the recent trend of evaluating progress on reinforcement learning technology by using text-based environments and games as evaluation environments. This reliance on text brings advances in natural language processing into the ambit of these agents, with a recurring thread being the use of external knowledge to mimic and better human-level performance. We present one such instantiation of agents that use commonsense knowledge from ConceptNet to show promising performance on two text-based environments.
References in corpus (9)
- Semi-Supervised Classification with Graph Convolutional Networks
- ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
- Sample Efficient Actor-Critic with Experience Replay
- Towards Deep Symbolic Reinforcement Learning
- Language Understanding for Text-based Games Using Deep Reinforcement Learning
- TextWorld: A Learning Environment for Text-based Games
- Learning Dynamic Belief Graphs to Generalize on Text-Based Games
- Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
Cited by in corpus (8)
- How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds
- Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
- Playing Text-Based Games with Common Sense
- WordCraft: An Environment for Benchmarking Commonsense Agents
- An Overview of Natural Language State Representation for Reinforcement Learning
- Learning Knowledge Graph-based World Models of Textual Environments
- Modeling Worlds in Text
- Generalization in Text-based Games via Hierarchical Reinforcement Learning