Natural Language Reinforcement Learning
Abstract
Reinforcement Learning (RL) mathematically formulates decision-making with Markov Decision Process (MDP). With MDPs, researchers have achieved remarkable breakthroughs across various domains, including games, robotics, and language models. This paper seeks a new possibility, Natural Language Reinforcement Learning (NLRL), by extending traditional MDP to natural language-based representation space. Specifically, NLRL innovatively redefines RL principles, including task objectives, policy, value function, Bellman equation, and policy iteration, into their language counterparts. With recent advancements in large language models (LLMs), NLRL can be practically implemented to achieve RL-like policy and value improvement by either pure prompting or gradient-based training. Experiments over Maze, Breakthrough, and Tic-Tac-Toe games demonstrate the effectiveness, efficiency, and interpretability of the NLRL framework among diverse use cases. Our code will be released at https://github.com/waterhorse1/Natural-language-RL.
- Publication:
-
arXiv e-prints
- Pub Date:
- November 2024
- DOI:
- 10.48550/arXiv.2411.14251
- arXiv:
- arXiv:2411.14251
- Bibcode:
- 2024arXiv241114251F
- Keywords:
-
- Computer Science - Machine Learning;
- Computer Science - Artificial Intelligence;
- Computer Science - Computation and Language
- E-Print:
- Extension of arXiv:2402.07157