Using evaluation functions in Monte-Carlo tree search

DOI10.1016/J.TCS.2016.06.026MaRDI QIDQ307789zbMATHOpenAlexFDO

Authors Richard J. Lorentz

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.2016.06.026

zbMATH Keywords

AmazonsBreakthroughHavannahMCTSMCTS-EPT

Mathematics Subject Classification ID

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

Recommendations

• MCTS-minimax hybrids with state evaluations
• Amazons Discover Monte-Carlo
• Monte-Carlo Tree Search Solver
• PROGRESSIVE STRATEGIES FOR MONTE-CARLO TREE SEARCH
• Score bounded Monte-Carlo tree search

Cites work

• Amazons Discover Monte-Carlo
• An analysis of alpha-beta pruning
• An evaluation function for the game of amazons
• PROGRESSIVE STRATEGIES FOR MONTE-CARLO TREE SEARCH

Cited in

(25)

• Information capture and reuse strategies in Monte Carlo Tree Search, with applications to games of hidden information
• On Monte-Carlo tree search for deterministic games with alternate moves and complete information
• PROGRESSIVE STRATEGIES FOR MONTE-CARLO TREE SEARCH
• Pruning playouts in Monte Carlo tree search for the game of Havannah
• Analyzing simulations in Monte-Carlo tree search for the game of Go
• Anomalies of pure Monte-Carlo search in Monte-Carlo perfect games
• Heuristic function evaluation framework
• On Monte Carlo tree search and reinforcement learning
• Amazons Discover Monte-Carlo
• Monte-Carlo simulation balancing in practice
• Improving Monte-Carlo tree search in Havannah
• VOI-aware MCTS
• Scalability and parallelization of Monte-Carlo tree search
• Score bounded Monte-Carlo tree search
• Node-expansion operators for the UCT algorithm
• Monte-Carlo opening books for Amazons
• Exploring search space trees using an adapted version of Monte Carlo tree search for combinatorial optimization problems
• Monte-Carlo Tree Search Solver
• Computational experiments with the RAVE heuristic
• Enhancements for multi-player Monte-Carlo tree search
• MCTS-minimax hybrids with state evaluations
• Adaptive playouts for online learning of policies during Monte Carlo tree search
• An analysis for strength improvement of an MCTS-based program playing Chinese dark chess
• Playout policy adaptation with move features
• Monte-Carlo approximiation of temperature

This page was built for publication: Using evaluation functions in Monte-Carlo tree search

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q307789)