• Publications
  • Influence
Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search
  • Rémi Coulom
  • Computer Science, Mathematics
  • Computers and Games
  • 29 May 2006
TLDR
A Monte-Carlo evaluation consists in estimating a position by averaging the outcome of several random continuations. Expand
  • 886
  • 133
  • PDF
Computing "Elo Ratings" of Move Patterns in the Game of Go
  • Rémi Coulom
  • Computer Science
  • J. Int. Comput. Games Assoc.
  • 2007
TLDR
This paper presents a new Bayesian technique for supervised learning of such patterns from game records, based on a generalization of Elo ratings. Expand
  • 281
  • 38
  • PDF
Reinforcement Learning Using Neural Networks, with Applications to Motor Control. (Apprentissage par renforcement utilisant des réseaux de neurones, avec des applications au contrôle moteur)
TLDR
This thesis is a study of practical methods to estimate value functions with feedforward neural networks in model-based reinforcement learning. Expand
  • 107
  • 9
Whole-History Rating: A Bayesian Rating System for Players of Time-Varying Strength
  • Rémi Coulom
  • Computer Science
  • Computers and Games
  • 29 September 2008
TLDR
Whole-History Rating (WHR) is a new method to estimate the time-varying strengths of players involved in paired comparisons. Expand
  • 54
  • 6
  • PDF
CLOP: Confident Local Optimization for Noisy Black-Box Parameter Tuning
TLDR
We propose a new approach to local regression that overcomes all these problems in a straightforward and efficient way. Expand
  • 32
  • 3
  • PDF
Time Management for Monte-Carlo Tree Search Applied to the Game of Go
TLDR
This paper presents the effect on playing strength of a variety of time-management heuristics for 19x19 Go. Expand
  • 13
  • 3
  • PDF
Monte-Carlo Tree Search in Crazy Stone
Monte-Carlo tree search has recently revolutionized Go programming. Even on the large 19x19 board, the strongest Monte-Carlo programs are now stronger than the strongest classical programs. This talkExpand
  • 21
  • 3
Monte-Carlo Simulation Balancing in Practice
TLDR
Simulation balancing is a new technique to tune parameters of a playout policy for a Monte-Carlo game-playing program, without requiring any external expert to provide position evaluations. Expand
  • 48
  • 2
  • PDF
Reinforcement Learning Using Neural Networks
TLDR
Disclosed are a system and method for facilitating the setup of a nucleonic gauge and automatic controller for measuring and controlling the thickness of a material. Expand
  • 9
  • 2