no code implementations • ICML 2020 • Yuxuan Xie, Jilles Dibangoye, Olivier Buffet
Optimally solving decentralized partially observable Markov decision processes under either full or no information sharing received significant attention in recent years.
no code implementations • ICML 2020 • Yuxuan Xie, Jilles Dibangoye, Olivier Buffet
Optimally solving decentralized partially observable Markov decision processes under either full or no information sharing received significant attention in recent years.
no code implementations • 10 Feb 2023 • Manuel Alejandro Diaz-Zapata, David Sierra González, Özgür Erkent, Jilles Dibangoye, Christian Laugier
Semantic grids can be useful representations of the scene around an autonomous system.
no code implementations • 14 Nov 2022 • Manuel Alejandro Diaz-Zapata, Özgür Erkent, Christian Laugier, Jilles Dibangoye, David Sierra González
Semantic grids are a useful representation of the environment around a robot.
no code implementations • 25 Oct 2021 • 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.
1 code implementation • ECCV 2020 • Edward Beeching, Jilles Dibangoye, Olivier Simonin, Christian Wolf
We train an agent to navigate in 3D environments using a hierarchical strategy including a high-level graph based planner and a local policy.
no code implementations • 29 Jun 2020 • Olivier Buffet, Jilles Dibangoye, Aurélien Delage, Abdallah Saffidine, Vincent Thomas
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 recursively within the original problem.
no code implementations • 24 Jan 2020 • Edward Beeching, Christian Wolf, Jilles Dibangoye, Olivier Simonin
The EgoMap architecture incorporates several inductive biases including a differentiable inverse projection of CNN feature vectors onto a top-down spatially structured map.
1 code implementation • 3 Apr 2019 • Edward Beeching, Christian Wolf, Jilles Dibangoye, Olivier Simonin
In this paper we argue that research on training agents capable of complex reasoning can be simplified by decoupling from the requirement of high fidelity photographic observations.
no code implementations • NeurIPS 2018 • Mathieu Fehr, Olivier Buffet, Vincent Thomas, Jilles Dibangoye
In this paper, we focus on POMDPs and ρ-POMDPs with λ ρ -Lipschitz reward function, and demonstrate that, for finite horizons, the optimal value function is Lipschitz-continuous.
no code implementations • ICML 2018 • Jilles Dibangoye, Olivier Buffet
We address a long-standing open problem of reinforcement learning in decentralized partially observable Markov decision processes.
Multi-agent Reinforcement Learning reinforcement-learning +1