Monte Carlo Search

Introduction

This is the page for the Monte Carlo Search course of the master IASD.

Slides

Slides of the course: MonteCarlo.pdf.

References

Monte Carlo Tree Search

"A Survey of Monte Carlo Tree Search Methods", Cameron Browne et al. IEEE TCIAIG 2012. survey.pdf.

"Monte-Carlo tree search and rapid action value estimation in computer Go", Sylvain Gelly, David Silver. Artificial Intelligence, 2011 rave.pdf

"Generalized Rapid Action Value Estimation", Tristan Cazenave. IJCAI 2015, pp. 754-760. grave.pdf

Nested Monte Carlo Search

"Nested Monte-Carlo Search", T. Cazenave. IJCAI 2009, pp. 456-461, Pasadena, July 2009. nested.pdf

"Nested Monte Carlo Search for Two-player Games", Tristan Cazenave, Abdallah Saffidine, Michael Schofield, Michael Thielscher. AAAI 2016, pp. 687-693. 12134-55519-1-PB.pdf

Playout Policy Adaptation

"Nested Rollout Policy Adaptation for Monte Carlo Tree Search", Christopher Rosin. IJCAI 2011. nrpa.pdf

"Playout Policy Adaptation with Move Features", Tristan Cazenave. Theoretical Computer Science, Vol. 644, pp. 43-52, 2016. ppatcs.pdf

Zero Learning

"A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play", David Silver et al. Science 2018. alphazero.pdf

"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model", Julian Schrittwieser et al. 2019. muzero.pdf

"Accelerating Self-Play Learning in Go", David J. Wu. AAAI RLG 2020. accelerating.pdf

"Polygames: Improved Zero Learning", Tristan Cazenave et al. 2020. polygames.pdf