Thesis

Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes Timothée LESORT Arxiv

Articles and Preprint

State representation learning for control: An overview (2018)
T Lesort, N Díaz-Rodríguez, JF Goudou, D Filliat, Neural Networks Article arXiv pdf bib

Generative Models from the perspective of Continual Learning (2018)
T Lesort, H Caselles-Dupré, M Garcia-Ortiz, A Stoian, D Filliat, IJCNN 2019 arXiv

Unsupervised state representation learning with robotic priors: a robustness benchmark (2017)
Timothée Lesort, Mathieu Seurin, Xinrui Li, Natalia Díaz Rodríguez, David Filliat, IJCNN 2019 pdf

Exploring to learn visual saliency: The RL-IAC approach (2019)
C Craye, T Lesort, D Filliat, JF Goudou, Robotics and Autonomous Systems arXiv

Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics (2018)
A Raffin, A Hill, KR Traoré, T Lesort, N Díaz-Rodríguez, D Filliat, ICLR 2019 Workshop on “Structure & Priors in Reinforcement Learning” (SPiRL) arXiv

S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning (2018)
A Raffin, A Hill, R Traoré, T Lesort, N Díaz-Rodríguez, D Filliat, NeurIPS 2018 Workshop on “Deep Reinforcement Learning” arXiv

Training Discriminative Models to Evaluate Generative Ones (2018)
T Lesort, JF Goudou, A Stoian, D Filliat, ICANN 2019 arXiv

Marginal Replay vs Conditional Replay for Continual Learning (2018)
T Lesort, A Gepperth, A Stoian, D Filliat, ICANN 2019 arXiv

DisCoRL: Continual Reinforcement Learning via Policy Distillation (2019)
R Traoré, H Caselles-Dupré, T Lesort, T Sun, N Diaz-Rodriguez, D Filliat, NeurIPS 2019 Workshop on “Reinforcement Learning” arXiv

Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer (2019)
R Traoré, H Caselles-Dupré, T Lesort, T Sun, N Diaz-Rodriguez, D Filliat, ICML 2019 Workshop on “Multi-Task and Lifelong Reinforcement Learning” arXiv

Continual Learning of Generative Models with Maximum Entropy Generative Replay (2019)
C Sübakan, M Caccia, T Lesort, Laurent Charlin, ICML 2019 Workshop on “Multi-Task and Lifelong Reinforcement Learning”

Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges (2019)
T Lesort, V Lomonaco, A Stoian, D Maltoni, D Filliat, N Díaz-Rodríguez Information Fusion arXiv

Regularization Shortcomings for Continual Learning (2019)
Timothée Lesort, Andrei Stoian, David Filliat