Matthieu Zimmer
Matthieu Zimmer
University of Michigan-Shanghai Jiao Tong University Joint Institute
Bekræftet mail på matthieu-zimmer.net - Startside
Titel
Citeret af
Citeret af
År
Teacher-student framework: a reinforcement learning approach
M Zimmer, P Viappiani, P Weng
AAMAS Workshop Autonomous Robots and Multirobot Systems, 2014
452014
Bootstrapping Q-Learning for Robotics from Neuro-Evolution Results
M Zimmer, S Doncieux
IEEE Transactions on Cognitive and Developmental Systems, 2017
182017
Neural Fitted Actor-Critic
M Zimmer, Y Boniface, A Dutech
ESANN - European Symposium on Artificial Neural Networks, Computational …, 2016
122016
Learning Fair Policies in Multi-Objective (Deep) Reinforcement Learning with Average and Discounted Rewards
U Siddique, P Weng, M Zimmer
International Conference on Machine Learning, 8905-8915, 2020
92020
Invariant transform experience replay: Data augmentation for deep reinforcement learning
Y Lin, J Huang, M Zimmer, Y Guan, J Rojas, P Weng
IEEE Robotics and Automation Letters 5 (4), 6615-6622, 2020
92020
Exploiting the sign of the advantage function to learn deterministic policies in continuous domains
M Zimmer, P Weng
International Joint Conference on Artificial Intelligence, 2019
82019
Developmental reinforcement learning through sensorimotor space enlargement
M Zimmer, Y Boniface, A Dutech
International Conference on Development and Learning and on Epigenetic Robotics, 2018
82018
Apprentissage par renforcement développemental
M Zimmer
Université de Lorraine, 2018
62018
Learning fair policies in decentralized cooperative multi-agent reinforcement learning
M Zimmer, C Glanois, U Siddique, P Weng
International Conference on Machine Learning, 12967-12978, 2021
42021
Towards More Sample Efficiency inReinforcement Learning with Data Augmentation
Y Lin, J Huang, M Zimmer, J Rojas, P Weng
Robot Learning Workshop, NeurIPS 2019, 2019
22019
Invariant transform experience replay
Y Lin, J Huang, M Zimmer, J Rojas, P Weng
arXiv preprint arXiv:1909.10707, 2019
12019
Off-Policy Neural Fitted Actor-Critic
M Zimmer, Y Boniface, A Dutech
Deep Reinforcement Learning Workshop, NIPS 2016, 2016
12016
Toward a data efficient neural actor-critic
M Zimmer, Y Boniface, A Dutech
European Workshop on Reinforcement Learning, 2016
12016
Hyperparameter Auto-Tuning in Self-Supervised Robotic Learning
J Huang, J Rojas, M Zimmer, H Wu, Y Guan, P Weng
IEEE Robotics and Automation Letters 6 (2), 3537-3544, 2021
2021
Differentiable Logic Machines
M Zimmer, X Feng, C Glanois, Z Jiang, J Zhang, P Weng, L Dong, ...
arXiv preprint arXiv:2102.11529, 2021
2021
An efficient reinforcement learning algorithm for learning deterministic policies in continuous domains
M Zimmer, P Weng
Proceedings of the First International Conference on Distributed Artificial …, 2019
2019
Apprentissage par renforcement développemental.(Developmental reinforcement learning).
M Zimmer
University of Lorraine, Nancy, France, 2018
2018
Vers des architectures acteur-critique neuronales efficaces en données
M Zimmer, Y Boniface, A Dutech
Journées Francophones sur la Planification, la Décision et l'Apprentissage …, 2016
2016
Construction Automatique d’État et d’Actions en Apprentissage par Renforcement
M Zimmer, S Doncieux
2014
Exploration de la notion de méta-apprentissage
M Zimmer, Y Boniface, A Dutech, N Rougier
2012
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–20