Picture for Alexandre Laterre

Alexandre Laterre

Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function

Nov 19, 2022
Clément Bonnet, Laurence Midgley, Alexandre Laterre

Figure 1 for Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function

Figure 2 for Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function

Figure 3 for Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function

Figure 4 for Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function

* Published at the 6th Workshop on Meta-Learning at NeurIPS 2022, New Orleans

Access Paper or Ask Questions

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

May 28, 2022
Christopher W. F. Parsonson, Alexandre Laterre, Thomas D. Barrett

Figure 1 for Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories

Figure 2 for Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories

Figure 3 for Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories

Figure 4 for Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories

* 10 pages, 4 figures, 1 table, and supplementary material

Access Paper or Ask Questions

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

Oct 30, 2021
Clément Bonnet, Paul Caron, Thomas Barrett, Ian Davies, Alexandre Laterre

Figure 1 for One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning

Figure 2 for One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning

Figure 3 for One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning

Figure 4 for One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning

* 14 pages, 6 figures, 2 tables

Access Paper or Ask Questions

Offline Reinforcement Learning Hands-On

Nov 29, 2020
Louis Monier, Jakub Kmec, Alexandre Laterre, Thomas Pierrot, Valentin Courgeau, Olivier Sigaud, Karim Beguir

Figure 1 for Offline Reinforcement Learning Hands-On

Figure 2 for Offline Reinforcement Learning Hands-On

Figure 3 for Offline Reinforcement Learning Hands-On

Figure 4 for Offline Reinforcement Learning Hands-On

* Accepted at NeurIPS 2020 Offline Reinforcement Learning Workshop. First two authors contributed equally. Authors three and four advised equally

Access Paper or Ask Questions

A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

Oct 15, 2020
Arnu Pretorius, Scott Cameron, Elan van Biljon, Tom Makkink, Shahil Mawjee, Jeremy du Plessis, Jonathan Shock, Alexandre Laterre, Karim Beguir

Figure 1 for A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

Figure 2 for A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

Figure 3 for A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

Figure 4 for A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

* 17 pages, 16 Figures, to appear in Advances of Neural Information Processing Systems (NeurIPS) conference, 2020

Access Paper or Ask Questions