3260 papers • 126 benchmarks • 313 datasets
Chess is a two-player strategy board game played on a chessboard, a checkered gameboard with 64 squares arranged in an 8×8 grid. The idea of making a machine that could beat a Grandmaster human player was a fascination in the artificial community for decades. Famously IBM's DeepBlue beat Kasparov in the 1990s. More recently more human-like approaches such as AlphaZero have appeared.
(Image credit: Papersgraph)
These leaderboards are used to track progress in game-of-chess-14
No benchmarks available.
Use these libraries to find game-of-chess-14 models and implementations
No datasets available.
No subtasks available.
This paper generalises the approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains, and convincingly defeated a world-champion program in each case.
The MuZero algorithm is presented, which, by combining a tree-based search with a learned model, achieves superhuman performance in a range of challenging and visually complex domains, without any knowledge of their underlying dynamics.
An end-to-end learning method for chess, relying on deep neural networks, which relies entirely on datasets of several million chess games, and no further domain specific knowledge is incorporated.
It is found that with enough training data, transformer language models can learn to track pieces and predict legal moves with high accuracy when trained solely on move sequences and for small training sets providing access to board state information during training can yield significant improvements.
This paper introduces a new large-scale chess commentary dataset and proposes an end-to-end trainable neural model which takes into account multiple pragmatic aspects of the game state that may be commented upon to describe a given chess move.
A deep neural network is trained to serve as a static evaluation function, which is accompanied by a relatively simple look ahead algorithm, and it is shown that this function has encoded some semblance of look ahead knowledge, and is comparable to classical evaluation functions.
Adding a benchmark result helps the community track progress.