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.

PDF] Monte-Carlo Graph Search for AlphaZero

From alpha go to alpha zero TLP innova 2018

Monte Carlo tree search - Wikipedia

Monte-Carlo Tree Search Explained

LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios – arXiv Vanity

Why Player Of Games Is Needed. Comparison Between Player of Games…, by Ben Bellerose

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

Reusability report: Comparing gradient descent and Monte Carlo tree search optimization of quantum annealing schedules

PDF] Monte-Carlo Graph Search for AlphaZero