Publications (sorted by type)

International Journals

[1] Jiancong Huang, Juan Rojas, Matthieu Zimmer, Hongmin Wu, Yisheng Guan, and Paul Weng. Hyperparameter auto-tuning in self-supervised robotic learning. IEEE Robotics and Automation Letters, 2021.
[ bib | pdf | source code ]
[2] Yijiong Lin, Jiancong Huang, Matthieu Zimmer, Juan Rojas, and Paul Weng. Invariant transform experience replay. IEEE Robotics and Automation Letters, 2020.
[ bib | video | pdf | source code ]
[3] Matthieu Zimmer and Stephane Doncieux. Bootstrapping q-learning for robotics from neuro-evolution results. IEEE Transactions on Cognitive and Developmental Systems, 2017.
[ bib | video | hal pdf | pdf ]
International Conferences

[1] Matthieu Zimmer*, Claire Glanois*, Umer Siddique, and Paul Weng. Learning fair policies in decentralized cooperative multi-agent reinforcement learning. In International Conference on Machine Learning, 2021.
[ bib | arXiv | source code ]
[2] Umer Siddique, Paul Weng, and Matthieu Zimmer. Learning fair policies in multi-objective deep reinforcement learning with average and discounted rewards. In International Conference on Machine Learning, 2020.
[ bib | pdf | source code ]
[3] Matthieu Zimmer and Paul Weng. An efficient reinforcement learning algorithm for learning deterministic policies in continuous domains. In Distributed Artificial Intelligence, September 2019.
[ bib | hal pdf | pdf | source code ]
[4] Matthieu Zimmer and Paul Weng. Exploiting the sign of the advantage function to learn deterministic policies in continuous domains. In International Joint Conferences on Artificial Intelligence, August 2019.
[ bib | poster | hal pdf | source code | slides ]
[5] Matthieu Zimmer, Yann Boniface, and Alain Dutech. Developmental reinforcement learning through sensorimotor space enlargement. In The 8th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, September 2018.
[ bib | video | hal pdf | source code | slides ]
[6] Matthieu Zimmer, Yann Boniface, and Alain Dutech. Neural fitted actor-critic. In ESANN – European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, April 2016.
[ bib | data | poster | hal pdf | pdf | source code ]
Work in progress

[1] Matthieu Zimmer, Xuening Feng, Claire Glanois, Zhaohui Jiang, Jianyi Zhang, Paul Weng, Li Dong, Hao Jianye, and Liu Wulong. Differentiable logic machines. 2021.
[ bib | arXiv | source code ]
International Workshops

[1] Jiancong Huang, Juan Rojas, Matthieu Zimmer, Hongmin Wu, Yisheng Guan, and Paul Weng. Hyperparameter auto-tuning in self-supervised robotic learning. In Deep Reinforcement Learning Workshop – NeurIPS 2020, 2020.
[ bib | video | pdf | source code ]
[2] Yijiong Lin, Jiancong Huang, Matthieu Zimmer, Juan Rojas, and Paul Weng. Towards more sample efficiency in reinforcement learning with data augmentation. In Robot Learning: Control and Interaction in the Real World – NeurIPS workshop, December 2019.
[ bib | pdf | source code ]
[3] Matthieu Zimmer, Yann Boniface, and Alain Dutech. Off-policy neural fitted actor-critic. In Deep Reinforcement Learning Workshop, NeurIPS 2016, 10 December 2016.
[ bib | poster | pdf ]
[4] Matthieu Zimmer, Yann Boniface, and Alain Dutech. Toward a data efficient neural actor-critic. In European Workshop on Reinforcement Learning, 4 December 2016.
[ bib | poster | hal pdf | pdf ]
[5] Matthieu Zimmer, Paolo Viappiani, and Paul Weng. Teacher-student framework: a reinforcement learning approach. In AAMAS Workshop Autonomous Robots and Multirobot Systems, 2014.
[ bib | pdf | source code | slides ]
National Conferences

[1] Matthieu Zimmer, Yann Boniface, and Alain Dutech. Vers des architectures acteur-critique neuronales efficaces en données. In Journées Francophones sur la Planification, la Décision et l’Apprentissage pour la conduite de systèmes, July 2016.
[ bib | video | hal pdf | slides ]
Theses and Various Reports

[1] Matthieu Zimmer. Apprentissage par renforcement développemental. PhD thesis, University of Lorraine, January 2018.
[ bib | video | hal pdf | meta | pdf | source code | slides ]
[2] Matthieu Zimmer. Construction automatique d’état et d’actions en apprentissage par renforcement. Master’s thesis, University Pierre and Marie Curie, 2014.
[ bib ]
[3] Matthieu Zimmer, Yann Boniface, Alain Dutech, and Nicolas Rougier. Dans quelle mesure un système apprenant peut prendre conscience de ses performances et altérer son comportement. Research Report, 2012.
[ bib | hal pdf ]