Search Machine Learning Repository:
All publications by Bruno Scherrer
authors venues years



On the Rate of Convergence and Error Bounds for LSTD($\lambda$)
Manel Tagorti and Bruno Scherrer
Proceedings of the 32nd International Conference on Machine Learning (ICML-15), 2015


Approximate Dynamic Programming for Two-Player Zero-Sum Markov Games
Julien Perolat, Bruno Scherrer, Bilal Piot and Olivier Pietquin
Proceedings of the 32nd International Conference on Machine Learning (ICML-15), 2015


Non-Stationary Approximate Modified Policy Iteration
Boris Lesner and Bruno Scherrer
Proceedings of the 32nd International Conference on Machine Learning (ICML-15), 2015


Approximate Policy Iteration Schemes: A Comparison
Bruno Scherrer
Proceedings of the 31st International Conference on Machine Learning (ICML-14), 2014


Approximate Dynamic Programming Finally Performs Well in the Game of Tetris
Victor Gabillon, Mohammad Ghavamzadeh and Bruno Scherrer
Advances in Neural Information Processing Systems 26, 2013


Improved and Generalized Upper Bounds on the Complexity of Policy Iteration
Bruno Scherrer
Advances in Neural Information Processing Systems 26, 2013


On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes
Bruno Scherrer and Boris Lesner
Advances in Neural Information Processing Systems 25, 2012


Approximate Modified Policy Iteration
Bruno Scherrer, Mohammad Ghavamzadeh, Victor Gabillon and Matthieu Geist
Proceedings of the 29th International Conference on Machine Learning (ICML-12), 2012


A Dantzig Selector Approach to Temporal Difference Learning
Matthieu Geist, Bruno Scherrer, Alessandro Lazaric and Mohammad Ghavamzadeh
Proceedings of the 29th International Conference on Machine Learning (ICML-12), 2012


Classification-based Policy Iteration with a Critic
Victor Gabillon, Alessandro Lazaric, Mohammad Ghavamzadeh and Bruno Scherrer
Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011


Least-Squares Policy Iteration: Bias-Variance Trade-off in Control Problems
Christophe Thiery and Bruno Scherrer
Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010


Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view
Bruno Scherrer
Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010


Biasing Approximate Dynamic Programming with a Lower Discount Factor
Marek Petrik and Bruno Scherrer
Advances in Neural Information Processing Systems 21, 2008