Playout policy adaptation with move features

DOI10.1016/J.TCS.2016.06.024MaRDI QIDQ307774zbMATH OpenOpenAlexFDO

Authors Tristan Cazenave

Publication date 5 September 2016

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2016.06.024

zbMATH Keywords

machine learningMonte Carlo tree searchcomputer gamesplayout policy

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Combinatorial games (91A46)

Recommendations

• Adaptive playouts for online learning of policies during Monte Carlo tree search
• Using evaluation functions in Monte-Carlo tree search
• Pruning playouts in Monte Carlo tree search for the game of Havannah
• General game playing with stochastic CSP
• On Monte Carlo tree search and reinforcement learning

Cites work

• Biasing Monte-Carlo simulations through RAVE values
• MoHex 2.0: a pattern-based MCTS hex player
• Monte-Carlo simulation balancing in practice

Cited in

(2)

• Adaptive playouts for online learning of policies during Monte Carlo tree search
• Spatial state-action features for general games

Describes a project that uses

Uses Software

• MoHex

This page was built for publication: Playout policy adaptation with move features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q307774)