This model serves as a language value function in Natural Language Reinforcement Learning (NLRL) framework, specifically trained for the TicTacToe game. It evaluates state-action pairs through natural language description and provides value assessment.
This model can be used as a TicTacToe position evaluator that explains its evaluation through natural language before providing the final assessment. The model generates both reasoning chains and final value judgments.
This model is specifically trained for TicTacToe state-action evaluation and should not be used for other games or value assessment tasks.
Training data consists of state-action pairs collected through NLRL actor-critic learning process, with language-based Monte Carlo estimates serving as training targets for the value function.
1@misc{feng2024naturallanguagereinforcementlearning,
2 title={Natural Language Reinforcement Learning},
3 author={Xidong Feng and Ziyu Wan and Haotian Fu and Bo Liu and Mengyue Yang and Girish A. Koushik and Zhiyuan Hu and Ying Wen and Jun Wang},
4 year={2024},
5 eprint={2411.14251},
6 archivePrefix={arXiv},
7 primaryClass={cs.LG},
8 url={https://arxiv.org/abs/2411.14251},
9}
