A
Arpad Rimmel
Researcher at Université Paris-Saclay
Publications - 39
Citations - 805
Arpad Rimmel is an academic researcher from Université Paris-Saclay. The author has contributed to research in topics: Monte Carlo tree search & Computer Go. The author has an hindex of 13, co-authored 35 publications receiving 772 citations. Previous affiliations of Arpad Rimmel include CentraleSupélec & French Institute for Research in Computer Science and Automation.
Papers
More filters
Journal ArticleDOI
The Computational Intelligence of MoGo Revealed in Taiwan's Computer Go Tournaments
Chang-Shing Lee,Mei-Hui Wang,Guillaume Chaslot,Jean-Baptiste Hoock,Arpad Rimmel,Olivier Teytaud,Shang-Rong Tsai,Shun-Chin Hsu,Tzung-Pei Hong +8 more
TL;DR: The results reveal that MoGo can reach the level of 3 Dan (3D) with: (1) good skills for fights, (2) weaknesses in corners, in particular, for "semeai" situations, and (3) strengths in favorable situations such as handicap games.
Journal ArticleDOI
Current Frontiers in Computer Go
TL;DR: It is seen that in 9 × 9, computers are very close to the best human level, and can be improved easily for the opening book; whereas in 19 × 19, handicap 7 is not enough for the computers to win against top level professional players, due to some clearly understood weaknesses of the current algorithms.
Proceedings ArticleDOI
Bandit-based optimization on graphs with application to library performance tuning
TL;DR: A novel algorithm is proposed that solves the problem of choosing fast implementations for a class of recursive algorithms such as the fast Fourier transforms by reducing it to maximizing an objective function over the sinks of a directed acyclic graph.
Book ChapterDOI
Adding expert knowledge and exploration in monte-carlo tree search
TL;DR: A new exploration term, more efficient than classical UCT-like exploration terms, which combines efficiently expert rules, patterns extracted from datasets, All-Moves-As-First values, and classical online values is presented.
Book ChapterDOI
Optimization of the nested Monte-Carlo algorithm on the traveling salesman problem with time windows
TL;DR: This paper proposes to use the nested Monte-Carlo algorithm combined with a Self-Adaptation Evolution Strategy to solve the traveling salesman problem with time windows and shows that with this technique it can reach the state of the art solutions for a lot of problems in a short period of time.