Search Results for author: Alexandre Laterre

Found 13 papers, 6 papers with code

Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories

1 code implementation28 May 2022 Christopher W. F. Parsonson, Alexandre Laterre, Thomas D. Barrett

By retrospectively deconstructing the search tree into multiple paths each contained within a sub-tree, we enable the agent to learn from shorter trajectories with more predictable next states.

Imitation Learning reinforcement-learning

Learning to Solve Combinatorial Graph Partitioning Problems via Efficient Exploration

1 code implementation27 May 2022 Thomas D. Barrett, Christopher W. F. Parsonson, Alexandre Laterre

Compared to the nearest competitor, ECORD reduces the optimality gap by up to 73% on 500 vertex graphs with a decreased wall-clock time.

Efficient Exploration graph partitioning

One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning

no code implementations30 Oct 2021 Clément Bonnet, Paul Caron, Thomas Barrett, Ian Davies, Alexandre Laterre

Self-tuning algorithms that adapt the learning process online encourage more effective and robust learning.

Learning to Solve Combinatorial Problems via Efficient Exploration

no code implementations29 Sep 2021 Thomas D Barrett, Christopher William Falke Parsonson, Alexandre Laterre

Compared to the nearest competitor, ECORD reduces the optimality gap by up to 73% on 500 vertex graphs with a decreased wall-clock time.

Efficient Exploration

Designing a Prospective COVID-19 Therapeutic with Reinforcement Learning

no code implementations3 Dec 2020 Marcin J. Skwark, Nicolás López Carranza, Thomas Pierrot, Joe Phillips, Slim Said, Alexandre Laterre, Amine Kerkeni, Uğur Şahin, Karim Beguir

This suggests that combining leading protein design methods with modern deep reinforcement learning is a viable path for discovering a Covid-19 cure and may accelerate design of peptide-based therapeutics for other diseases.

reinforcement-learning

Offline Reinforcement Learning Hands-On

no code implementations29 Nov 2020 Louis Monier, Jakub Kmec, Alexandre Laterre, Thomas Pierrot, Valentin Courgeau, Olivier Sigaud, Karim Beguir

Offline Reinforcement Learning (RL) aims to turn large datasets into powerful decision-making engines without any online interactions with the environment.

Behavioural cloning Decision Making +2

Learning Compositional Neural Programs for Continuous Control

no code implementations27 Jul 2020 Thomas Pierrot, Nicolas Perrin, Feryal Behbahani, Alexandre Laterre, Olivier Sigaud, Karim Beguir, Nando de Freitas

Third, the self-models are harnessed to learn recursive compositional programs with multiple levels of abstraction.

Continuous Control

Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization

2 code implementations4 Jul 2018 Alexandre Laterre, Yunguan Fu, Mohamed Khalil Jabri, Alain-Sam Cohen, David Kas, Karl Hajjar, Torbjorn S. Dahl, Amine Kerkeni, Karim Beguir

Results from applying the R2 algorithm to instances of a two-dimensional and three-dimensional bin packing problems show that it outperforms generic Monte Carlo tree search, heuristic algorithms and integer programming solvers.

Combinatorial Optimization reinforcement-learning

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