ChessGPT：連接策略學習與語言建模

摘要

在解決決策任務時，人類通常依賴兩個關鍵信息來源：(1) 歷史政策數據，提供與環境互動的重播，以及 (2) 自然語言形式的分析洞察，揭示寶貴的思考過程或戰略考量。儘管如此，先前的大部分研究都僅聚焦於一個信息來源：它們要麼僅使用歷史重播來直接學習政策或價值函數，要麼從事語言模型訓練，僅利用語言語料庫。在本文中，我們主張一個強大的自主代理應該涵蓋這兩個來源。因此，我們提出了ChessGPT，一個將政策學習和語言建模相結合的GPT模型，通過整合來自這兩個來源的數據在象棋遊戲中。具體來說，我們構建了一個與象棋相關的大規模遊戲和語言數據集。利用這個數據集，我們展示了兩個模型示例ChessCLIP和ChessGPT，整合了政策學習和語言建模。最後，我們提出了一個完整的評估框架，用於評估語言模型在象棋方面的能力。實驗結果驗證了我們模型和數據集的有效性。我們在https://github.com/waterhorse1/ChessGPT上開源了我們的代碼、模型和數據集。

English

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.

ChessGPT：連接策略學習與語言建模

ChessGPT: Bridging Policy Learning and Language Modeling

摘要

Support