Bruno Scherrer

70 papers A* 17A 4B 3Misc 1Journal 33Unranked 10

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	AlphaBeta is not as good as you think: a new probabilistic model to better analyze deterministic game-solving algorithms. CoRR Raphaël Boige, Amine M. Boumaza, Bruno Scherrer
2021	J	`jnl`	Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm. CoRR Lin Chen, Bruno Scherrer, Peter L. Bartlett
2020	A*	`conf`	Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning. NeurIPS Nino Vieillard, Tadashi Kozuno, Bruno Scherrer, Olivier Pietquin, Rémi Munos, Matthieu Geist
2020	J	`jnl`	Leverage the Average: an Analysis of Regularization in RL. CoRR Nino Vieillard, Tadashi Kozuno, Bruno Scherrer, Olivier Pietquin, Rémi Munos, Matthieu Geist
2020	A	`conf`	Momentum in Reinforcement Learning. AISTATS Nino Vieillard, Bruno Scherrer, Olivier Pietquin, Matthieu Geist
2019	A*	`conf`	A Theory of Regularized Markov Decision Processes. ICML Matthieu Geist, Bruno Scherrer, Olivier Pietquin
2019	J	`jnl`	A Theory of Regularized Markov Decision Processes. CoRR Matthieu Geist, Bruno Scherrer, Olivier Pietquin
2019	A*	`conf`	How to Combine Tree-Search Methods in Reinforcement Learning. AAAI Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2019	J	`jnl`	Momentum in Reinforcement Learning. CoRR Nino Vieillard, Bruno Scherrer, Olivier Pietquin, Matthieu Geist
2019	—	`conf`	Stability guarantees for nonlinear discrete-time systems controlled by approximate value iteration. CDC Romain Postoyan, Mathieu Granzotto, Lucian Busoniu, Bruno Scherrer, Dragan Nesic, Jamal Daafouz
2018	J	`jnl`	Anderson Acceleration for Reinforcement Learning. CoRR Matthieu Geist, Bruno Scherrer
2018	J	`jnl`	Beyond the One Step Greedy Approach in Reinforcement Learning. CoRR Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2018	A*	`conf`	Beyond the One-Step Greedy Approach in Reinforcement Learning. ICML Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2018	J	`jnl`	How to Combine Tree-Search Methods in Reinforcement Learning. CoRR Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2018	A*	`conf`	Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning. NeurIPS Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2018	J	`jnl`	Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning. CoRR Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor
2016	—	`book`	Contributions algorithmiques au contrôle optimal stochastique à temps discret et horizon infini. Bruno Scherrer
2016	J	`jnl`	Improved and Generalized Upper Bounds on the Complexity of Policy Iteration. Math. Oper. Res. Bruno Scherrer
2016	A	`conf`	On the Use of Non-Stationary Strategies for Solving Two-Player Zero-Sum Markov Games. AISTATS Julien Pérolat, Bilal Piot, Bruno Scherrer, Olivier Pietquin
2016	A*	`conf`	Softened Approximate Policy Iteration for Markov Games. ICML Julien Pérolat, Bilal Piot, Matthieu Geist, Bruno Scherrer, Olivier Pietquin
2015	A*	`conf`	Approximate Dynamic Programming for Two-Player Zero-Sum Markov Games. ICML Julien Pérolat, Bruno Scherrer, Bilal Piot, Olivier Pietquin
2015	J	`jnl`	Approximate modified policy iteration and its application to the game of Tetris. J. Mach. Learn. Res. Bruno Scherrer, Mohammad Ghavamzadeh, Victor Gabillon, Boris Lesner, Matthieu Geist
2015	A*	`conf`	Non-Stationary Approximate Modified Policy Iteration. ICML Boris Lesner, Bruno Scherrer
2015	A*	`conf`	On the Rate of Convergence and Error Bounds for LSTD(\(\lambda\)). ICML Manel Tagorti, Bruno Scherrer
2015	J	`jnl`	Recherche locale de politique dans un espace convexe. Rev. d'Intelligence Artif. Bruno Scherrer, Matthieu Geist
2014	A*	`conf`	Approximate Policy Iteration Schemes: A Comparison. ICML Bruno Scherrer
2014	J	`jnl`	Approximate Policy Iteration Schemes: A Comparison. CoRR Bruno Scherrer
2014	—	`conf`	Local Policy Search in a Convex Space and Conservative Policy Iteration as Boosted Policy Search. ECML/PKDD (3) Bruno Scherrer, Matthieu Geist
2014	J	`jnl`	Modified policy iteration algorithms are not strongly polynomial for discounted dynamic programming. Oper. Res. Lett. Eugene A. Feinberg, Jefferson Huang, Bruno Scherrer
2014	J	`jnl`	Off-policy learning with eligibility traces: a survey. J. Mach. Learn. Res. Matthieu Geist, Bruno Scherrer
2014	J	`jnl`	Rate of Convergence and Error Bounds for LSTD(λ). CoRR Manel Tagorti, Bruno Scherrer
2013	—	`conf`	Approximate Dynamic Programming Finally Performs Well in the Game of Tetris. NIPS Victor Gabillon, Mohammad Ghavamzadeh, Bruno Scherrer
2013	—	`conf`	Improved and Generalized Upper Bounds on the Complexity of Policy Iteration. NIPS Bruno Scherrer
2013	J	`jnl`	Improved and Generalized Upper Bounds on the Complexity of Policy Iteration. CoRR Bruno Scherrer
2013	J	`jnl`	Off-policy Learning with Eligibility Traces: A Survey CoRR Matthieu Geist, Bruno Scherrer
2013	J	`jnl`	On the Performance Bounds of some Policy Search Dynamic Programming Algorithms. CoRR Bruno Scherrer
2013	J	`jnl`	Performance bounds for λ policy iteration and application to the game of Tetris. J. Mach. Learn. Res. Bruno Scherrer
2013	J	`jnl`	Policy Search: Any Local Optimum Enjoys a Global Performance Guarantee. CoRR Bruno Scherrer, Matthieu Geist
2013	J	`jnl`	Tight Performance Bounds for Approximate Modified Policy Iteration with Non-Stationary Policies CoRR Boris Lesner, Bruno Scherrer
2012	A*	`conf`	A Dantzig Selector Approach to Temporal Difference Learning. ICML Matthieu Geist, Bruno Scherrer, Alessandro Lazaric, Mohammad Ghavamzadeh
2012	J	`jnl`	Approximate Modified Policy Iteration CoRR Bruno Scherrer, Victor Gabillon, Mohammad Ghavamzadeh, Matthieu Geist
2012	A*	`conf`	Approximate Modified Policy Iteration. ICML Bruno Scherrer, Victor Gabillon, Mohammad Ghavamzadeh, Matthieu Geist
2012	J	`jnl`	On the Use of Non-Stationary Policies for Infinite-Horizon Discounted Markov Decision Processes CoRR Bruno Scherrer
2012	J	`jnl`	On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes CoRR Bruno Scherrer, Boris Lesner
2012	—	`conf`	On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes. NIPS Bruno Scherrer, Boris Lesner
2011	A*	`conf`	Classification-based Policy Iteration with a Critic. ICML Victor Gabillon, Alessandro Lazaric, Mohammad Ghavamzadeh, Bruno Scherrer
2011	—	`conf`	Recursive Least-Squares Learning with Eligibility Traces. EWRL Bruno Scherrer, Matthieu Geist
2011	—	`conf`	ℓ1-Penalized Projected Bellman Residual. EWRL Matthieu Geist, Bruno Scherrer
2010	A*	`conf`	Least-Squares Policy Iteration: Bias-Variance Trade-off in Control Problems. ICML Christophe Thiery, Bruno Scherrer
2010	J	`jnl`	Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view CoRR Bruno Scherrer
2010	A*	`conf`	Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view. ICML Bruno Scherrer
2009	J	`jnl`	Building Controllers for Tetris. ICGA J. Christophe Thiery, Bruno Scherrer
2009	J	`jnl`	Construction d'un joueur artificiel pour Tetris. Rev. d'Intelligence Artif. Christophe Thiery, Bruno Scherrer
2009	J	`jnl`	Improvements on Learning Tetris with Cross Entropy. ICGA J. Christophe Thiery, Bruno Scherrer
2008	J	`jnl`	Analyse d'un algorithme d'intelligence en essaim pour le fourragement. Rev. d'Intelligence Artif. Amine M. Boumaza, Bruno Scherrer
2008	—	`conf`	Biasing Approximate Dynamic Programming with a Lower Discount Factor. NIPS Marek Petrik, Bruno Scherrer
2008	—	`conf`	Embedded Harmonic Control for Trajectory Planning in Large Environments. ReConFig César Torres-Huitzil, Bernard Girau, Amine M. Boumaza, Bruno Scherrer
2007	B	`conf`	Convergence and rate of convergence of a foraging ant model. IEEE Congress on Evolutionary Computation Amine M. Boumaza, Bruno Scherrer
2007	A	`conf`	Convergence and rate of convergence of a simple ant model. AAMAS Amine M. Boumaza, Bruno Scherrer
2007	A*	`conf`	Optimal control subsumes harmonic control. ICRA Amine M. Boumaza, Bruno Scherrer
2007	J	`jnl`	Performance Bounds for Lambda Policy Iteration CoRR Bruno Scherrer
2006	J	`jnl`	Modular self-organization CoRR Bruno Scherrer
2005	J	`jnl`	Asynchronous neurocomputing for optimal control and reinforcement learning with large state spaces. Neurocomputing Bruno Scherrer
2003	—	`—`	Apprentissage de représentation et auto-organisation modulaire pour un agent autonome. Bruno Scherrer
2003	A*	`conf`	Modular self-organization for a long-living autonomous agent. IJCAI Bruno Scherrer
2003	B	`conf`	Parallel asynchronous distributed computations of optimal control in large state space Markov Decision processes. ESANN Bruno Scherrer
2003	—	`conf`	Planning Cooperative Homogeneous Multiagent Systems Using Markov Decision Processes. ICEIS (2) Iadine Chades, Bruno Scherrer, François Charpillet
2002	Misc	`conf`	A heuristic approach for solving decentralized-POMDP: assessment on the pursuit problem. SAC Iadine Chades, Bruno Scherrer, François Charpillet
2002	A	`conf`	Coevolutive planning in markov decision processes. AAMAS Bruno Scherrer, François Charpillet
2002	B	`conf`	Cooperative Co-Learning: A Model-Based Approach for Solving Multi Agent Reinforcement Problems. ICTAI Bruno Scherrer, François Charpillet