When solving decision-making tasks, humans typically depend on information from two key sources: (1) Historical policy data, which provides interaction replay from the environment, and (2) Analytical insights in natural language form, exposing the invaluable thought process or strategic considerations. Despite this, the majority of preceding research focuses on only one source: they either use historical replay exclusively to directly learn policy or value functions, or engaged in language model training utilizing mere language corpus. In this paper, we argue that a powerful autonomous agent should cover both sources. Thus, we propose ChessGPT, a GPT model bridging policy learning and language modeling by integrating data from these two sources in Chess games. Specifically, we build a large-scale game and language dataset related to chess. Leveraging the dataset, we showcase two model examples ChessCLIP and ChessGPT, integrating policy learning and language modeling. Finally, we propose a full evaluation framework for evaluating language model's chess ability. Experimental results validate our model and dataset's effectiveness. We open source our code, model, and dataset at https://github.com/waterhorse1/ChessGPT.

翻译：在解决决策任务时，人类通常依赖两个关键来源的信息：（1）历史策略数据，提供与环境互动的回放；（2）自然语言形式的分析洞察，揭示宝贵的思考过程或战略考量。尽管如此，先前的大多数研究仅聚焦于其中一个来源：要么仅利用历史回放直接学习策略或价值函数，要么仅使用纯语言语料进行语言模型训练。本文提出，一个强大的自主智能体应覆盖这两个来源。因此，我们提出了ChessGPT，一个通过整合国际象棋游戏中这两个来源的数据，弥合策略学习与语言建模的GPT模型。具体而言，我们构建了一个与国际象棋相关的大规模游戏与语言数据集。利用该数据集，我们展示了两个模型示例：ChessCLIP和ChessGPT，它们整合了策略学习与语言建模。最后，我们提出了一个完整的评估框架，用于评估语言模型的下棋能力。实验结果验证了我们的模型与数据集的有效性。我们在https://github.com/waterhorse1/ChessGPT上开源了我们的代码、模型和数据集。