Feng, Xidong; Luo, Yicheng; Wang, Ziyan; Tang, Hongrui; Yang, Mengyue; Shao, Kun; Mguni, David; ... Wang, Jun; + view all Feng, Xidong; Luo, Yicheng; Wang, Ziyan; Tang, Hongrui; Yang, Mengyue; Shao, Kun; Mguni, David; Du, Yali; Wang, Jun; - view fewer (2023) ChessGPT: Bridging Policy Learning and Language Modeling. In: Oh, A and Neumann, T and Globerson, A and Saenko, K and Hardt, M and Levine, S, (eds.) Advances in Neural Information Processing Systems 36 (NeurIPS 2023). NeurIPS Proceedings: New Orleans, LA, USA.

Preview

Text 2306.09200v2.pdf - Accepted Version Download (2MB) | Preview

Abstract

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.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item