Language is Power: Representing States Using Natural Language in Reinforcement Learning
This addresses the problem of scalability in reinforcement learning for AI researchers, offering a novel approach to state representation that could enhance performance in complex environments.
The paper tackles the challenge of high-dimensional tasks in reinforcement learning by representing states using natural language instead of raw visual inputs, showing that natural language-based agents in ViZDoom are more robust, converge faster, and perform better than vision-based agents.
Recent advances in reinforcement learning have shown its potential to tackle complex real-life tasks. However, as the dimensionality of the task increases, reinforcement learning methods tend to struggle. To overcome this, we explore methods for representing the semantic information embedded in the state. While previous methods focused on information in its raw form (e.g., raw visual input), we propose to represent the state using natural language. Language can represent complex scenarios and concepts, making it a favorable candidate for representation. Empirical evidence, within the domain of ViZDoom, suggests that natural language based agents are more robust, converge faster and perform better than vision based agents, showing the benefit of using natural language representations for reinforcement learning.