# DeepChess: End-to-End Deep Neural Network for Automatic Learning in Chess

arXiv: https://arxiv.org/abs/1711.09667 · HTML: https://mlsanity.com/paper/1711.09667/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2017.

## Built on by (most cited first, 14 of 14)

- [Chess as a Testbed for Language Model State Tracking](https://mlsanity.com/paper/2102.13249/) (2021)
- [Amortized Planning with Large-Scale Transformers: A Case Study on Chess](https://mlsanity.com/paper/2402.04494/) (2024)
- [Open- and Closed-Loop Neural Network Verification using Polynomial Zonotopes](https://mlsanity.com/paper/2207.02715/) (2022)
- [Leaky Nets: Recovering Embedded Neural Network Models and Inputs through Simple Power and Timing Side-Channels -- Attacks and Defenses](https://mlsanity.com/paper/2103.14739/) (2021)
- [Learning to Play Chess from Textbooks (LEAP): a Corpus for Evaluating Chess Moves based on Sentiment Analysis](https://mlsanity.com/paper/2310.20260/) (2023)
- [Aspect-based Sentiment Evaluation of Chess Moves (ASSESS): an NLP-based Method for Evaluating Chess Strategies from Textbooks](https://mlsanity.com/paper/2405.06499/) (2024)
- [Neural Network-based Information Set Weighting for Playing Reconnaissance Blind Chess](https://mlsanity.com/paper/2407.05864/) (2024)
- [Gapoera: Application Programming Interface for AI Environment of Indonesian Board Game](https://mlsanity.com/paper/2110.11924/) (2021)
- [Alpha-Mini: Minichess Agent with Deep Reinforcement Learning](https://mlsanity.com/paper/2112.13666/) (2021)
- [Extreme Multi-Domain, Multi-Task Learning With Unified Text-to-Text Transfer Transformers](https://mlsanity.com/paper/2209.10106/) (2022)
- [Global Convergence of Policy Gradient for Entropy Regularized Linear-Quadratic Control with Multiplicative Noise](https://mlsanity.com/paper/2510.02896/) (2025)
- [PARL: Prompt-based Agents for Reinforcement Learning](https://mlsanity.com/paper/2510.21306/) (2025)
- [From Probabilities to Decisions: Search and Multi-Teacher Distillation with Jev](https://mlsanity.com/paper/2610.09188/) (2026)
- [Learning to Play: Reinforcement Learning and Games](https://mlsanity.com/paper/2610.17391/) (2026)

## Abstract (arXiv)

We present an end-to-end learning method for chess, relying on deep neural networks. Without any a priori knowledge, in particular without any knowledge regarding the rules of chess, a deep neural network is trained using a combination of unsupervised pretraining and supervised training. The unsupervised training extracts high level features from a given position, and the supervised training learns to compare two chess positions and select the more favorable one. The training relies entirely on datasets of several million chess games, and no further domain specific knowledge is incorporated. The experiments show that the resulting neural network (referred to as DeepChess) is on a par with state-of-the-art chess playing programs, which have been developed through many years of manual feature selection and tuning. DeepChess is the first end-to-end machine learning-based method that results in a grandmaster-level chess playing performance.