Get started
Author

Bruno Scherrer

Observed names: B. Scherrer, Scherrer, Bruno
Observed institutions: Centre National de la Recherche Scientifique, Institut national de recherche en sciences et technologies du numérique, Institut Élie Cartan de Lorraine, Laboratoire Lorrain de Recherche en Informatique et ses Applications, Centre Inria de l'Université de Lorraine, Laboratoire Interdisciplinaire des Environnements Continentaux, MIT Computer Science and Artificial Intelligence Laboratory, Université de Lorraine
ORCID: 0000-0001-6097-4489
Observed ORCID: 0000-0001-6097-4489
OpenAlex ID: A5032281855
A Theory of Regularized Markov Decision Processes
2019 · Geist, Matthieu, Scherrer, Bruno, et al. · arXiv (Cornell University) · 146
PDF
Approximate modified policy iteration and its application to the game of Tetris
2015 · Bruno Scherrer, Mohammad Ghavamzadeh, et al. · 69
Approximate dynamic programming for two-player zero-sum Markov games
2015 · Perolat, Julien, Scherrer, Bruno, et al. · HAL · 63
Approximate Policy Iteration Schemes: A Comparison
2014 · Scherrer, Bruno · arXiv (Cornell University) · 50
PDF
Improved and Generalized Upper Bounds on the Complexity of Policy Iteration
2016 · Bruno Scherrer · Mathematics of Operations Research · 46
PDF
Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view
2010 · Scherrer, Bruno · arXiv (Cornell University) · 45
PDF
Approximate Dynamic Programming Finally Performs Well in the Game of Tetris
2013 · Victor Gabillon, Mohammad Ghavamzadeh, et al. · 43
Biasing Approximate Dynamic Programming with a Lower Discount Factor
2008 · Marek Petrik, Bruno Scherrer, et al. · 43
Building Controllers for Tetris
2009 · Christophe Thiery, Bruno Scherrer · ICGA Journal · 42
Improvements on Learning Tetris with Cross Entropy
2009 · Christophe Thiery, Bruno Scherrer · ICGA Journal · 38
PDF
A heuristic approach for solving decentralized-POMDP
2002 · Iadine Chades, Bruno Scherrer, et al. · ACM Symposium on Applied Computing · 36
Anderson Acceleration for Reinforcement Learning
2018 · Geist, Matthieu, Scherrer, Bruno · arXiv (Cornell University) · 28
PDF
Approximate Modified Policy Iteration
2012 · Scherrer, Bruno, Gabillon, Victor, et al. · arXiv (Cornell University) · 28
PDF
Local Policy Search in a Convex Space and Conservative Policy Iteration as Boosted Policy Search
2014 · Bruno Scherrer, Matthieu Geist · Lecture notes in computer science · 26
PDF
Least-Squares Policy Iteration: Bias-Variance Trade-off in Control Problems
2010 · Christophe Thiéry, Bruno Scherrer · International Conference on Machine Learning · 26
Softened approximate policy iteration for Markov games
2016 · Pérolat, Julien, Piot, Bilal, et al. · LillOA (Université de Lille (University Of Lille)) · 25
PDF
A Dantzig Selector Approach to Temporal Difference Learning
2012 · Geist, Matthieu, Scherrer, Bruno, et al. · arXiv (Cornell University) · 25
PDF
ℓ1-Penalized Projected Bellman Residual
2012 · Matthieu Geist, Bruno Scherrer · Lecture notes in computer science · 25
Beyond the One Step Greedy Approach in Reinforcement Learning
2018 · Efroni, Yonathan, Dalal, Gal, et al. · arXiv (Cornell University) · 24
PDF
Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning
2020 · Vieillard, Nino, Kozuno, Tadashi, et al. · HAL · 23
Leverage the Average: an Analysis of KL Regularization in RL
2020 · Vieillard, Nino, Kozuno, Tadashi, et al. · arXiv (Cornell University) · 22
PDF
Author manuscript, published in "International Conference on Machine Learning (ICML) (2011)" Classification-based Policy Iteration with a Critic
2011 · Victor Gabillon, Ro Lazaric, et al. · 19
How to Combine Tree-Search Methods in Reinforcement Learning
2019 · Yonathan Efroni, Gal Dalal, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 17
On the Use of Non-Stationary Strategies for Solving Two-Player Zero-Sum Markov Games
2016 · Pérolat, Julien, Piot, Bilal, et al. · HAL · 17
Momentum in Reinforcement Learning
2019 · Vieillard, Nino, Scherrer, Bruno, et al. · arXiv (Cornell University) · 16
PDF
Works count: 127
Citation count: 1,130
H-index: 21
I10-index: 32
Year
Topic
Type