1 citations · 2 across the 6 of their papers we have counts for
6 papers
Efficient Matroid Bandit Linear Optimization Leveraging Unimodality
Aurélien Delage, Romaric Gaudel
We study the combinatorial semi-bandit problem under matroid constraints. The regret achieved by recent approaches is optimal, in the sense that it matches the lower bound. Yet, ti…
Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach
Johan Peralez, Aurèlien Delage, Jacopo Castellini +2
The centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to -optimally solving decentralized partially observable Markov decision p…
Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach
Johan Peralez, Aurélien Delage, Olivier Buffet +1
A recent theory shows that a multi-player decentralized partially observable Markov decision process can be transformed into an equivalent single-player game, enabling the applicat…
HSVI can solve zero-sum Partially Observable Stochastic Games
Aurélien Delage, Olivier Buffet, Jilles S. Dibangoye +1
State-of-the-art methods for solving 2-player zero-sum imperfect information games rely on linear programming or regret minimization, though not on dynamic programming (DP) or heur…
HSVI for zs-POSGs using Concavity, Convexity and Lipschitz Properties
Aurélien Delage, Olivier Buffet, Jilles Dibangoye
Dynamic programming and heuristic search are at the core of state-of-the-art solvers for sequential decision-making problems. In partially observable or collaborative settings (\eg…
On Bellman's Optimality Principle for zs-POSGs
Olivier Buffet, Jilles Dibangoye, Aurélien Delage +2
Many non-trivial sequential decision-making problems are efficiently solved by relying on Bellman's optimality principle, i.e., exploiting the fact that sub-problems are nested rec…