Zobrazeno 1 - 10
of 3 149
pro vyhledávání: '"P Cazenave"'
Autor:
Roucairol, Milo, Cazenave, Tristan
We are interested in the automatic refutation of spectral graph theory conjectures. Most existing works address this problem either with the exhaustive generation of graphs with a limited size or with deep reinforcement learning. Exhaustive generatio
Externí odkaz:
http://arxiv.org/abs/2409.18626
With the aim of improving performance in Markov Decision Problem in an Off-Policy setting, we suggest taking inspiration from what is done in Offline Reinforcement Learning (RL). In Offline RL, it is a common practice during policy learning to mainta
Externí odkaz:
http://arxiv.org/abs/2408.10113
The job shop scheduling problem (JSSP) remains a significant hurdle in optimizing production processes. This challenge involves efficiently allocating jobs to a limited number of machines while minimizing factors like total processing time or job del
Externí odkaz:
http://arxiv.org/abs/2408.06993
Imperfect information games, such as Bridge and Skat, present challenges due to state-space explosion and hidden information, posing formidable obstacles for search algorithms. Determinization-based algorithms offer a resolution by sampling hidden in
Externí odkaz:
http://arxiv.org/abs/2408.02380
Publikováno v:
2023 IEEE Conference on Games (CoG)
In imperfect information games (e.g. Bridge, Skat, Poker), one of the fundamental considerations is to infer the missing information while at the same time avoiding the disclosure of private information. Disregarding the issue of protecting private i
Externí odkaz:
http://arxiv.org/abs/2405.14346
Publikováno v:
International Conference on the Applications of Evolutionary Computation (Part of EvoStar), 2023, 753--764
In recent years, much progress has been made in computer Go and most of the results have been obtained thanks to search algorithms (Monte Carlo Tree Search) and Deep Reinforcement Learning (DRL). In this paper, we propose to use and analyze the lates
Externí odkaz:
http://arxiv.org/abs/2405.14265
Autor:
Cazenave, Tristan
Monte Carlo Tree Search and Monte Carlo Search have good results for many combinatorial problems. In this paper we propose to use Monte Carlo Search to design mathematical expressions that are used as exploration terms for Monte Carlo Tree Search alg
Externí odkaz:
http://arxiv.org/abs/2404.09304
Autor:
Cazenave, Tristan
Monte Carlo Search gives excellent results in multiple difficult combinatorial problems. Using a prior to perform non uniform playouts during the search improves a lot the results compared to uniform playouts. Handmade heuristics tailored to the comb
Externí odkaz:
http://arxiv.org/abs/2401.10431
Autor:
Cazenave, Tristan
Generalized Nested Rollout Policy Adaptation (GNRPA) is a Monte Carlo search algorithm for optimizing a sequence of choices. We propose to improve on GNRPA by avoiding too deterministic policies that find again and again the same sequence of choices.
Externí odkaz:
http://arxiv.org/abs/2401.10420
Monte Carlo Tree Search can be used for automated theorem proving. Holophrasm is a neural theorem prover using MCTS combined with neural networks for the policy and the evaluation. In this paper we propose to improve the performance of the Holophrasm
Externí odkaz:
http://arxiv.org/abs/2309.12711