← Authors

Bruno Scherrer

19 papers · 2008–2020 · 5 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (11) 🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (12) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐺 Lone Wolf (3) 🧬 Topic Evolution πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (73) πŸ“ˆ Trend Setter πŸ’Ž Century Club (19) πŸ”₯ Unstoppable (5) πŸš€ Conference Pioneer

Conferences

ICML (7) NIPS (6) JMLR (3) AISTATS (2) AAAI (1)

Top co-authors

Matthieu Geist (6) Olivier Pietquin (6) Bilal Piot (3) Julien PΓ©rolat (3) Yonathan Efroni (3) Shie Mannor (3) Gal Dalal (3) Boris Lesner (3) Nino Vieillard (2) Mohammad Ghavamzadeh (2)

Keywords

reinforcement learning (9) policy iteration (9) markov decision process (8) value iteration (8) approximate dynamic programming (5) discount factor (4) value function approximation (4) markov game (3) non-stationary policy (3) value function (2) optimal control (2) policy optimization (2) eligibility trace (2) game ai (2) markov decision processes (2) zero-sum game (2) policy learning (2) policy improvement (2) approximate policy iteration (2) iteration complexity (2)

Papers

Momentum in Reinforcement Learning AISTATS 2020
Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning NIPS 2020
A Theory of Regularized Markov Decision Processes ICML 2019
How to Combine Tree-Search Methods in Reinforcement Learning AAAI 2019
Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning NIPS 2018
Beyond the One-Step Greedy Approach in Reinforcement Learning ICML 2018
Softened Approximate Policy Iteration for Markov Games ICML 2016
On the Use of Non-Stationary Strategies for Solving Two-Player Zero-Sum Markov Games AISTATS 2016
On the Rate of Convergence and Error Bounds for LSTD(Ξ») ICML 2015
Approximate Modified Policy Iteration and its Application to the Game of Tetris JMLR 2015
Approximate Dynamic Programming for Two-Player Zero-Sum Markov Games ICML 2015
Non-Stationary Approximate Modified Policy Iteration ICML 2015
Approximate Policy Iteration Schemes: A Comparison ICML 2014
Off-policy Learning With Eligibility Traces: A Survey JMLR 2014
Approximate Dynamic Programming Finally Performs Well in the Game of Tetris NIPS 2013
Improved and Generalized Upper Bounds on the Complexity of Policy Iteration NIPS 2013
Performance Bounds for Ξ» Policy Iteration and Application to the Game of Tetris JMLR 2013
On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes NIPS 2012
Biasing Approximate Dynamic Programming with a Lower Discount Factor NIPS 2008