Empirical evaluation of AlphaGo Zero. a Performance of self-play
Por um escritor misterioso
Last updated 26 abril 2025

Applied Sciences, Free Full-Text

Frontiers AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong

PPT - Algorithms for solving sequential (zero-sum) complete-information games PowerPoint Presentation - ID:9554145

Mastering the game of Go without human knowledge

Extracting tactics learned from self-play in general games - ScienceDirect

PDF] Accelerating Self-Play Learning in Go

Student of Games: A unified learning algorithm for both perfect and imperfect information games

A (Long) Peek into Reinforcement Learning

AlphaGo and AlphaGo Zero

Extracting tactics learned from self-play in general games - ScienceDirect

AlphaGo and AlphaGo Zero