Adaptive playouts for online learning of policies during Monte Carlo tree search

DOI10.1016/J.TCS.2016.06.029MaRDI QIDQ307776zbMATH OpenOpenAlexFDO

Authors Tobias Graf, Marco Platzner

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.2016.06.029

zbMATH Keywords

reinforcement learningMonte Carlo tree searchcomputer Goadaptive playouts

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

• Playout policy adaptation with move features
• On Monte Carlo tree search and reinforcement learning
• Using evaluation functions in Monte-Carlo tree search
• Analyzing simulations in Monte-Carlo tree search for the game of Go
• PROGRESSIVE STRATEGIES FOR MONTE-CARLO TREE SEARCH

Cites work

• Algorithms for reinforcement learning.
• Efficiency of static knowledge bias in Monte-Carlo tree search
• Investigating the limits of Monte-Carlo tree search methods in computer Go
• Monte-Carlo simulation balancing in practice
• PROGRESSIVE STRATEGIES FOR MONTE-CARLO TREE SEARCH
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Using deep convolutional neural networks in Monte Carlo tree search
• Variance reduction techniques for gradient estimates in reinforcement learning

Cited in

(3)

• Analyzing simulations in Monte-Carlo tree search for the game of Go
• Playout policy adaptation with move features
• Monte-Carlo simulation balancing in practice

Describes a project that uses

Uses Software

• PACHI

This page was built for publication: Adaptive playouts for online learning of policies during Monte Carlo tree search

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q307776)