Program

Schedule thumbnail
Talks schedule (pdf)

10:00-10:25 Regularized Fitted Q-iteration: Application to Bounded Resource Planning - Amir massoud Farahmand, Mohammad Ghavamzadeh , Csaba Szepesvari and Shie Mannor.
10:25-10:50 Regularized Policy Iteration - Amir massoud Farahmand, Mohammad Ghavamzadeh , Csaba Szepesvari and Shie Mannor.
10:50-11:05 Break
11:05-11:30 Sample-Based Learning and Search with Permanent and Transient Memories - David Silver, Rich Sutton and Martin Mueller
11:30-11:55 Parameter Tuning by the Cross-Entropy Method - Guillaume Chaslot, Mark Winands, István Szita and Jaap van den Herik
11:55-12:20 Including expert knowledge in Bandit-Based Monte-Carlo planning, with application to Computer-Go - Louis Chatriot, Sylvain Gelly, Hoock Jean-Baptiste, Julien Perez, Arpad Rimmel and Olivier Teytaud
12:20-14:00 Lunch
14:15-14:40 United We Stand: Population Based Methods for Solving Unknown POMDPs - Noel Welsh and Jeremy Wyatt
14:40-15:05 Reinforcement Learning with History Lists - Stephan Timmer and Martin Riedmiller
15:05-15:30 A Near Optimal Policy for Channel Allocation in Cognitive Radio - Sarah Filippi, Olivier Cappé, Fabrice Clérot and Eric Moulines
15:30-15:45 Break
15:45-16:10 Evaluation of Batch-Mode Reinforcement Learning Methods for Solving DEC-MDPs with Changing Action Sets - Thomas Gabel and Martin Riedmiller
16:10-16:35 Solving Analytic Multi-Agent Stochastic Processes - Luke Dickens, Krysia Broda and Alessandra Russo
16:35-16:50 Break
16:50-18:30 Multi-Automata Learning (Tutorial) - Ann Nowe, Katja Verbeeck and Peter Vrancx
09:10-09:35 Multigrid Reinforcement Learning with Reward Shaping - Marek Grzes and Daniel Kudenko
09:35-10:00 Reinforcement Learning with the Use of Costly Features - Robby Goetschalckx, Scott Sanner and Kurt Driessens
10:00-10:25 Tile Coding based on Hyperplane Tiles - Daniele Loiacono and Pier Luca Lanzi
10:25-10:50 Using Decision Trees as the Answer Networks in Temporal Difference-Networks - Laura-Andreea Antanas, Kurt Driessens, Jan Ramon and Tom Croonenborghs
10:50-11:05 Break
11:05-11:30 The many faces of optimism: a unifying approach - Istvan Szita and Andras Lorincz
11:30-11:55 On Upper-Confidence Bound Policies for Non-Stationary Bandit Problems - Aurélien Garivier and Eric Moulines
11:55-12:20 Reinforcement Learning by Direct Optimal Value Estimation and Regret Minimization - Manuel Loth and Philippe Preux
12:20-14:00 Lunch
14:15-15:30 Invited talk - Rich Sutton
15:30-15:45 Break
15:45-16:10 Adaptive Treatment of Epilepsy via Batch-mode Reinforcement Learning - Arthur Guez, Robert Vincent, Massimo Avoli and Joelle Pineau
16:10-16:35 Variable selection for dynamic treatment regimes: a reinforcement learning approach - Raphael Fonteneau, Louis Wehenkel and Damien Ernst
16:35-17:00 Use of Reinforcement Learning in two real applications - Jose D. Martin-Guerrero, Emilio Soria, Marcelino Martínez, Antonio José Serrano, Rafael Magdalena and Juan Gómez-Sanchis
17:00-17:15 Break
17:15-17:40 Knows What It Knows: A Framework For Self-Aware Learning - Lihong Li, Michael Littman and Thomas Walsh
17:40-18:05 Reinforcement learning in the presence of rare events - Jordan Frank, Shie Mannor and Doina Precup
18:05-18:30 A Metric Analogue to MDP Homomorphisms - Jonathan Taylor, Doina Precup and Prakash Panangaden
09:00-10:00 Invited talk: Temporal Difference Methods: Perspectives and Extensions - Dimitri Bertsekas
10:00-10:25 New Error Bounds for Approximations from Projected Linear Equations - Huizhen Yu and Dimitri Bertsekas
10:25-10:50 Model-based Reinforcement Learning with State Aggregation - Cosmin Paduraru, Robert Kaplow, Doina Precup and Joelle Pineau
10:50-11:05 Break
11:05-11:30 Basis Expansion in Natural Actor Critic Methods - Sertan Girgin and Philippe Preux
11:30-11:55 Variable Metric Reinforcement Learning Methods Applied to the Noisy Mountain Car Problem - Verena Heidrich-Meisner and Christian Igel
11:55-12:20 Policy Learning – a uniﬁed perspective with applications in robotics - Jan Peters, Jens Kober and Duy Nguyen-Tuong
12:20-14:00 Lunch
14:15-14:50 Exploiting Additive Structure in Factored MDPs for Reinforcement Learning - Thomas Degris, Olivier Sigaud and Pierre-Henri Wuillemin
14:40-15:05 Hierarchical reinforcement learning in factored MDPs - Olga Kozlova, Olivier Sigaud and Christophe Meyer
15:05-15:30 Bayesian Reward Filtering - Matthieu Geist, Olivier Pietquin and Gabriel Fricout
15:30-15:45 Break
15:45-16:10 Transfer of Samples in Batch Reinforcement Learning - Alessandro Lazaric, Marcello Restelli and Andrea Bonarini
16:10-16:35 Privacy-Preserving Reinforcement Learning - Jun Sakuma, Shigenobu Kobayashi and Rebecca Wright
16:35-17:00 Multi-Agent Model-Based Reinforcement Learning Experiments in the Pursuit Evasion Game - Bruno Bouzy and Marc Metivier
17:00-17:15 Break
17:15-17:40 A Family of Reinforcement Learning Algorithms - Marco Wiering and Hado van Hasselt
17:40-18:05 Empirical Bernstein Stopping - Volodymir Mnih and Csaba Szepesvari
18:05-18:30 Rollout Sampling Approximate Policy Iteration -- Algorithms and Bounds for Sampling-based Approximate Policy Iteration - Christos Dimitrakakis and Michail Lagoudakis
09:00-10:00 Invited talk: Reinforcement Learning for Robotics - Jan Peters
10:00-10:25 Efficient Reinforcement Learning in Parameterized Models: Discrete Parameter Case - Kirill Dyagilev, Shie Mannor and Nahum Shimkin
10:25-10:50 Robustness Analysis of SARSA(lambda) - Marek Grzes and Daniel Kudenko
10:50-11:05 Break
11:05-11:30 Lazy planning under uncertainty by optimizing decisions on an ensemble of incomplete disturbance trees - Boris Defourny, Damien Ernst and Louis Wehenkel
11:30-11:55 Optimistic planning of deterministic systems - Jean-Francois Hren and Remi Munos
11:55-12:20 Policy Optimization by Implicit Probabilistic Simulation - Carl Rasmussen and Marc Deisenroth
12:20-14:00 Lunch
14:15-14:40 Reinforcement Learning of Perceptual Coupling for Motor Primitives - Jens Kober and Jan Peters
14:40-15:05 Applications of Reinforcement Learning to Structured Prediction - Francis Maes, Ludovic DENOYER and Patrick Gallinari
15:05-15:30 Policy Iteration for Learning an Exercise Policy for American Options - Yuxi Li and Dale Schuurmans
15:30-15:45 Break
15:45-16:10 Adaptive Aggregation for Reinforcement Learning with Efficient Exploration: Deterministic Domains - Andrey Bernstein and Nahum Shimkin
16:10-16:35 Approximate Policy Iteration for Generalized Semi-Markov Decision Processes: an Improved Algorithm - Emmanuel Rachelson, Patrick Fabiani and Frédérick Garcia
16:35-17:00 Markov Decision Processes with Arbitrary Reward Processes - Jia Yuan Yu, Shie Mannor and Nahum Shimkin
17:00-17:15 Break
17:15-17:40 Relational TD Reinforcement Learning - Christophe Rodrigues, Pierre Gérard and Céline Rouveiro
17:40-18:05 Reinforcement Learning with Markov Logic Networks - Weiwei Wang, Xingguo Chen and Yang Gao
18:05-18:30 Classifier-Based Policy Representation - Ioannis Rexakis and Michail Lagoudakis
09:00-18:30 Social events / workgroups

Personal tools

Program

lundi

mardi

mercredi

jeudi

vendredi