Grandmaster-Level Chess Without Search
- URL: http://arxiv.org/abs/2402.04494v1
- Date: Wed, 7 Feb 2024 00:36:24 GMT
- Title: Grandmaster-Level Chess Without Search
- Authors: Anian Ruoss, Gr\'egoire Del\'etang, Sourabh Medapati, Jordi Grau-Moya,
Li Kevin Wenliang, Elliot Catt, John Reid, Tim Genewein
- Abstract summary: We train a model with supervised learning on a dataset of 10 million chess games.
Our largest model reaches a Lichess blitz Elo of 2895 against humans.
A systematic investigation of model and dataset size shows that strong chess performance only arises at sufficient scale.
- Score: 9.5790772976207
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The recent breakthrough successes in machine learning are mainly attributed
to scale: namely large-scale attention-based architectures and datasets of
unprecedented scale. This paper investigates the impact of training at scale
for chess. Unlike traditional chess engines that rely on complex heuristics,
explicit search, or a combination of both, we train a 270M parameter
transformer model with supervised learning on a dataset of 10 million chess
games. We annotate each board in the dataset with action-values provided by the
powerful Stockfish 16 engine, leading to roughly 15 billion data points. Our
largest model reaches a Lichess blitz Elo of 2895 against humans, and
successfully solves a series of challenging chess puzzles, without any
domain-specific tweaks or explicit search algorithms. We also show that our
model outperforms AlphaZero's policy and value networks (without MCTS) and
GPT-3.5-turbo-instruct. A systematic investigation of model and dataset size
shows that strong chess performance only arises at sufficient scale. To
validate our results, we perform an extensive series of ablations of design
choices and hyperparameters.
Related papers
- Offline Imitation Learning Through Graph Search and Retrieval [57.57306578140857]
Imitation learning is a powerful machine learning algorithm for a robot to acquire manipulation skills.
We propose GSR, a simple yet effective algorithm that learns from suboptimal demonstrations through Graph Search and Retrieval.
GSR can achieve a 10% to 30% higher success rate and over 30% higher proficiency compared to baselines.
arXiv Detail & Related papers (2024-07-22T06:12:21Z) - Learning to Play Chess from Textbooks (LEAP): a Corpus for Evaluating
Chess Moves based on Sentiment Analysis [4.314956204483074]
This paper examines chess textbooks as a new knowledge source for enabling machines to learn how to play chess.
We developed the LEAP corpus, a first and new heterogeneous dataset with structured (chess move notations and board states) and unstructured data.
We performed empirical experiments that assess the performance of various transformer-based baseline models for sentiment analysis.
arXiv Detail & Related papers (2023-10-31T08:26:02Z) - End-to-End Chess Recognition [11.15543089335477]
Current approaches use a pipeline of separate, independent, modules such as chessboard detection, square localization, and piece classification.
We explore an end-to-end approach to directly predict the configuration from the image, thus avoiding the error accumulation of the sequential approaches.
In contrast to existing datasets that are synthetically rendered and have only limited angles, ChessReD has photographs captured from various angles using smartphone cameras.
Our approach in chess recognition on the introduced challenging benchmark dataset outperforms related approaches, successfully recognizing the chess pieces' configuration in 15.26% of ChessReD's test images.
arXiv Detail & Related papers (2023-10-06T08:30:20Z) - GAMMA: Generalizable Articulation Modeling and Manipulation for
Articulated Objects [53.965581080954905]
We propose a novel framework of Generalizable Articulation Modeling and Manipulating for Articulated Objects (GAMMA)
GAMMA learns both articulation modeling and grasp pose affordance from diverse articulated objects with different categories.
Results show that GAMMA significantly outperforms SOTA articulation modeling and manipulation algorithms in unseen and cross-category articulated objects.
arXiv Detail & Related papers (2023-09-28T08:57:14Z) - Retrieval-Enhanced Contrastive Vision-Text Models [61.783728119255365]
We propose to equip vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time.
Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP.
Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks.
arXiv Detail & Related papers (2023-06-12T15:52:02Z) - Multi-Robot Deep Reinforcement Learning for Mobile Navigation [82.62621210336881]
We propose a deep reinforcement learning algorithm with hierarchically integrated models (HInt)
At training time, HInt learns separate perception and dynamics models, and at test time, HInt integrates the two models in a hierarchical manner and plans actions with the integrated model.
Our mobile navigation experiments show that HInt outperforms conventional hierarchical policies and single-source approaches.
arXiv Detail & Related papers (2021-06-24T19:07:40Z) - Determining Chess Game State From an Image [19.06796946564999]
This paper puts forth a new dataset synthesised from a 3D model that is an order of magnitude larger than existing ones.
A novel end-to-end chess recognition system is presented that combines traditional computer vision techniques with deep learning.
The described system achieves an error rate of 0.23% per square on the test set, 28 times better than the current state of the art.
arXiv Detail & Related papers (2021-04-30T13:02:13Z) - Learning Chess Blindfolded: Evaluating Language Models on State Tracking [69.3794549747725]
We consider the task of language modeling for the game of chess.
Unlike natural language, chess notations describe a simple, constrained, and deterministic domain.
We find that transformer language models can learn to track pieces and predict legal moves with high accuracy when trained solely on move sequences.
arXiv Detail & Related papers (2021-02-26T01:16:23Z) - LiveChess2FEN: a Framework for Classifying Chess Pieces based on CNNs [0.0]
We have implemented a functional framework that automatically digitizes a chess position from an image in less than 1 second.
We have analyzed different Convolutional Neural Networks for chess piece classification and how to map them efficiently on our embedded platform.
arXiv Detail & Related papers (2020-12-12T16:48:40Z) - Playing Chess with Limited Look Ahead [0.0]
We train a deep neural network to serve as a static evaluation function.
We show that our static evaluation function has encoded some semblance of look ahead knowledge.
We show that, despite strict restrictions on look ahead depth, our engine recommends moves of equal strength in roughly $83%$ of our sample positions.
arXiv Detail & Related papers (2020-07-04T16:02:43Z) - Model-Based Reinforcement Learning for Atari [89.3039240303797]
We show how video prediction models can enable agents to solve Atari games with fewer interactions than model-free methods.
Our experiments evaluate SimPLe on a range of Atari games in low data regime of 100k interactions between the agent and the environment.
arXiv Detail & Related papers (2019-03-01T15:40:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.