no code implementations • 22 Sep 2023 • Marc Pierre, Quentin Cohen-Solal, Tristan Cazenave
Monte Carlo Tree Search can be used for automated theorem proving.
no code implementations • 8 Feb 2023 • Quentin Cohen-Solal, Tristan Cazenave
In this paper, we extend the Descent framework, which enables learning and planning in the context of two-player games with perfect information, to the framework of stochastic games.
no code implementations • 11 Sep 2021 • Quentin Cohen-Solal
In this article, we prove the completeness of the following game search algorithms: unbounded best-first minimax with completion and descent with completion, i. e. we show that, with enough time, they find the best game strategy.
no code implementations • 19 Dec 2020 • Quentin Cohen-Solal, Tristan Cazenave
Deep Reinforcement Learning (DRL) reaches a superhuman level of play in many complete information games.
no code implementations • 3 Aug 2020 • Quentin Cohen-Solal
Finally, we apply these different techniques to design program-players to the game of Hex (size 11 and 13) surpassing the level of Mohex 3HNN with reinforcement learning from self-play without knowledge.
no code implementations • 15 Jul 2020 • Quentin Cohen-Solal
In this paper, we focus on qualitative temporal sequences of topological information.