paper-with-me

Papers

Learning to Plan via Supervised Contrastive Learning and Strategic Interpolation: A Chess Case Study

2025-06-05 · Andrew Hamara, Greg Hamerly, Pablo Rivas, Andrew C. Freeman

Modern chess engines achieve superhuman performance through deep tree search and regressive evaluation, while human players rely on intuition to select candidate moves followed by a shallow search to validate them. To model this intuition-driven planning process, we train a transformer encoder using supervised contrastive learning to embed board states into a latent space structured by positional evaluation. In this space, distance reflects evaluative similarity, and visualized trajectories display interpretable transitions between game states. We demonstrate that move selection can occur entirely within this embedding space by advancing toward favorable regions, without relying on deep search. Despite using only a 6-ply beam search, our model achieves an estimated Elo rating of 2593. Performance improves with both model size and embedding dimensionality, suggesting that latent planning may offer a viable alternative to traditional search. Although we focus on chess, the proposed embedding-based planning method can be generalized to other perfect-information games where state evaluations are learnable. All source code is available at https://github.com/andrewhamara/SOLIS.

📄 PDF Abstract BibTeX arXiv:2506.04892

Code (1)

andrewhamara/solis 공식 구현 jax

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Latent Planning via Embedding Arithmetic: A Contrastive Approach to Strategic Reasoning

2025-11-12 · Andrew Hamara, Greg Hamerly, Pablo Rivas, Andrew C. Freeman arxiv

Planning in high-dimensional decision spaces is increasingly being studied through the lens of learned representations. Rather than training policies or value heads, we investigate whether planning can be carried out dir…

Contrastive Learning

Explore the Reasoning Capability of LLMs in the Chess Testbed

2024-11-11 · Shu Wang, Lei Ji, Renxi Wang, Wenxiao Zhao 외

Reasoning is a central capability of human intelligence. In recent years, with the advent of large-scale datasets, pretrained large language models have emerged with new capabilities, including reasoning. However, these …

ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models

2025-09-29 · Jincheng Liu, Sijun He, Jingjing Wu, Xiangsen Wang 외 arxiv

Recent large language models (LLMs) have shown strong reasoning capabilities. However, a critical question remains: do these models possess genuine strategic reasoning, or do they primarily excel at pattern recognition? …

Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess

2025-07-01 · Dongyoon Hwang, Hojoon Lee, Jaegul Choo, Dongmin Park 외 arxiv

While reinforcement learning (RL) for large language models (LLMs) has shown promise in mathematical reasoning, strategic reasoning for LLMs using RL remains largely unexplored. We investigate whether LLMs can develop st…

Reinforcement LearningKnowledge DistillationMathematical Reasoning

Grounded Chess Reasoning in Language Models via Master Distillation

2026-03-20 · Zhenwei Tang, Qianfeng Wen, Seth Grief-Albert, Yahya Elgabra 외 arxiv

Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel. We introduce a general framework for distilling expert system reasoning into natu…

Reinforcement Learning