Skip to content

Publications

2022

LUCIE
LUCIE: An Evaluation and Selection Method for Stochastic Problems
Erwan Lecarpentier, Paul Templier, Emmanuel Rachelson, Dennis G. Wilson
In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2022

PDF   Appendix   Code

2021

NAS
On Constrained Optimization in Differentiable Neural Architecture Search
Kaitlin Maile, Erwan Lecarpentier, Hervé Luga, Dennis G. Wilson
Submitted, 2021

arXiv

Lipschitz Continuity of Q^*
Lipschitz Lifelong Reinforcement Learning
Erwan Lecarpentier, David Abel, Kavosh Asadi, Yuu Jinnai, Emmanuel Rachelson, Michael L. Littman
In Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI 2021

AAAI   PDF   Poster   Code

2019

Risk-Averse tree
Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning
Erwan Lecarpentier and Emmanuel Rachelson
In Proceedings of the 33rd Conference on Neural Information Processing Systems, NeurIPS 2019

NeurIPS   PDF   Poster   Code

2018

Open Loop Search Tree
Open loop execution of tree-search algorithms
Erwan Lecarpentier, Guillaume Infantes, Charles Lesire, and Emmanuel Rachelson
In Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018

IJCAI   PDF   Code

2017

Glider trajectory
Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring
Erwan Lecarpentier, Sebastian Rapp, Marc Melo and Emmanuel Rachelson
Journées Francophones Planification, Décision et Apprentissage, JFPDA 2017

JFPDA   PDF   Code

PhD Thesis (2020)

Reinforcement Learning in Non-Stationary Environments. Erwan Lecarpentier. University of Toulouse, France. 2020 PDF