PDF] Monte-Carlo Graph Search for AlphaZero

A new, improved search algorithm for AlphaZero is introduced which generalizes the search tree to a directed acyclic graph, which enables information flow across different subtrees and greatly reduces memory consumption. The AlphaZero algorithm has been successfully applied in a range of discrete domains, most notably board games. It utilizes a neural network, that learns a value and policy function to guide the exploration in a Monte-Carlo Tree Search. Although many search improvements have been proposed for Monte-Carlo Tree Search in the past, most of them refer to an older variant of the Upper Confidence bounds for Trees algorithm that does not use a policy for planning. We introduce a new, improved search algorithm for AlphaZero which generalizes the search tree to a directed acyclic graph. This enables information flow across different subtrees and greatly reduces memory consumption. Along with Monte-Carlo Graph Search, we propose a number of further extensions, such as the inclusion of Epsilon-greedy exploration, a revised terminal solver and the integration of domain knowledge as constraints. In our evaluations, we use the CrazyAra engine on chess and crazyhouse as examples to show that these changes bring significant improvements to AlphaZero.

Acquisition of chess knowledge in AlphaZero

Monte Carlo Tree Search: a review of recent modifications and applications

Deep bidirectional intelligence: AlphaZero, deep IA-search, deep IA-infer, and TPC causal learning, Applied Informatics

AlphaGo Zero Explained In One Diagram, by David Foster, Applied Data Science

Deep bidirectional intelligence: AlphaZero, deep IA-search, deep IA-infer, and TPC causal learning, Applied Informatics

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

Monte Carlo Tree Search: a review of recent modifications and applications

Acquisition of chess knowledge in AlphaZero

PDF] Monte-Carlo Graph Search for AlphaZero

AlphaDDA: strategies for adjusting the playing strength of a fully trained AlphaZero system to a suitable human training partner [PeerJ]

Representation Matters: The Game of Chess Poses a Challenge to Vision Transformers – arXiv Vanity

Multiplayer AlphaZero – arXiv Vanity

PDF) Targeted Search Control in AlphaZero for Effective Policy Improvement

Learning to traverse over graphs with a Monte Carlo tree search-based self-play framework - ScienceDirect