Search Results for author: Tristan Cazenave

Found 22 papers, 0 papers with code

Dialogue avec Molière (Dialogue with Molière )

no code implementations JEP/TALN/RECITAL 2022 Guillaume Grosjean, Anna Pappa, Baptiste Roziere, Tristan Cazenave

A l’occasion du quatre-centième anniversaire de la naissance de Molière (1622-1673), nous présentons un agent conversationnel qui parle comme un personnage du théâtre de Molière.

Chatbot

Nested Search versus Limited Discrepancy Search

no code implementations1 Oct 2022 Tristan Cazenave

Limited Discrepancy Search (LDS) is a popular algorithm to search a state space with a heuristic to order the possible actions.

Refutation of Spectral Graph Theory Conjectures with Monte Carlo Search

no code implementations4 Jul 2022 Milo Roucairol, Tristan Cazenave

We demonstrate how Monte Carlo Search (MCS) algorithms, namely Nested Monte Carlo Search (NMCS) and Nested Rollout Policy Adaptation (NRPA), can be used to build graphs and find counter-examples to spectral graph theory conjectures in minutes.

Generalized Nested Rollout Policy Adaptation with Dynamic Bias for Vehicle Routing

no code implementations12 Nov 2021 Julien Sentuc, Tristan Cazenave, Jean-Yves Lucas

In this paper we present an extension of the Nested Rollout Policy Adaptation algorithm (NRPA), namely the Generalized Nested Rollout Policy Adaptation (GNRPA), as well as its use for solving some instances of the Vehicle Routing Problem.

Learning-based Preference Prediction for Constrained Multi-Criteria Path-Planning

no code implementations2 Aug 2021 Kevin Osanlou, Christophe Guettier, Andrei Bursuc, Tristan Cazenave, Eric Jacopin

The uncertain criterion represents the feasibility of driving through the path without requiring human intervention.

Constrained Shortest Path Search with Graph Convolutional Neural Networks

no code implementations2 Aug 2021 Kevin Osanlou, Christophe Guettier, Andrei Bursuc, Tristan Cazenave, Eric Jacopin

In this paper, we focus on shortest path search with mandatory nodes on a given connected graph.

Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search

no code implementations2 Aug 2021 Kevin Osanlou, Andrei Bursuc, Christophe Guettier, Tristan Cazenave, Eric Jacopin

More specifically, a graph neural network is used to assist the branch and bound algorithm in handling constraints associated with a desired solution path.

Batch Monte Carlo Tree Search

no code implementations9 Apr 2021 Tristan Cazenave

The transposition table contains the results of the inferences while the search tree contains the statistics of Monte Carlo Tree Search.

Game of Go

Improving Model and Search for Computer Go

no code implementations6 Feb 2021 Tristan Cazenave

The standard for Deep Reinforcement Learning in games, following Alpha Zero, is to use residual networks and to increase the depth of the network to get better results.

reinforcement-learning

Optimizing $αμ$

no code implementations29 Jan 2021 Tristan Cazenave, Swann Legras, Véronique Ventos

$\alpha\mu$ is a search algorithm which repairs two defaults of Perfect Information Monte Carlo search: strategy fusion and non locality.

Stabilized Nested Rollout Policy Adaptation

no code implementations10 Jan 2021 Tristan Cazenave, Jean-Baptiste Sevestre, Matthieu Toulemont

Nested Rollout Policy Adaptation (NRPA) is a Monte Carlo search algorithm for single player games.

Minimax Strikes Back

no code implementations19 Dec 2020 Quentin Cohen-Solal, Tristan Cazenave

Deep Reinforcement Learning (DRL) reaches a superhuman level of play in many complete information games.

reinforcement-learning

Mobile Networks for Computer Go

no code implementations23 Aug 2020 Tristan Cazenave

The architecture of the neural networks used in Deep Reinforcement Learning programs such as Alpha Zero or Polygames has been shown to have a great impact on the performances of the resulting playing engines.

Game of Go reinforcement-learning

Monte Carlo Inverse Folding

no code implementations20 May 2020 Tristan Cazenave, Thomas Fournier

The RNA Inverse Folding problem comes from computational biology.

Generalized Nested Rollout Policy Adaptation

no code implementations22 Mar 2020 Tristan Cazenave

Nested Rollout Policy Adaptation (NRPA) is a Monte Carlo search algorithm for single player games.

Traveling Salesman Problem

Monte Carlo Game Solver

no code implementations15 Jan 2020 Tristan Cazenave

We present a general algorithm to order moves so as to speedup exact game solvers.

online learning

The αμ Search Algorithm for the Game of Bridge

no code implementations18 Nov 2019 Tristan Cazenave, Véronique Ventos

{\alpha}{\mu} is an anytime heuristic search algorithm for incomplete information games that assumes perfect information for the opponents.

Cannot find the paper you are looking for? You can Submit a new open access paper.