PDF] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

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 game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains. Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi (Japanese chess) as well as Go, and convincingly defeated a world-champion program in each case.

Mastering Atari, Go, chess and shogi by planning with a learned model

papers

Simple Alpha Zero

PDF] Reinforcement Learning for Extended Reality: Designing Self-Play Scenarios

PDF) Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

PDF] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Shogi - Chessprogramming wiki

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Discovering faster matrix multiplication algorithms with reinforcement learning

PDF] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Mastering the game of Go with deep neural networks and tree search

Full article: Time management in a chess game through machine learning