An Overview of Natural Language State Representation for Reinforcement Learning
arXiv:2007.09774
Abstract
A suitable state representation is a fundamental part of the learning process in Reinforcement Learning. In various tasks, the state can either be described by natural language or be natural language itself. This survey outlines the strategies used in the literature to build natural language state representations. We appeal for more linguistically interpretable and grounded representations, careful justification of design decisions and evaluation of the effectiveness of different approaches.
Accepted to the ICML 2020 Workshop on Language in Reinforcement Learning (LaReL). 4 pages
References in corpus (8)
- Grounded Language Learning in a Simulated 3D World
- Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
- Gated-Attention Architectures for Task-Oriented Language Grounding
- From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
- Selecting the State-Representation in Reinforcement Learning
- The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning
- Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
- Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing