Publications & Reports
DELTA Project
First DELTA Meeting
Some presentations held during the Delta meeting (10/4/18) at Inria Lilles
Second DELTA Meeting
Here are the presentations of the meeting held in Liège on the 30th of April
JAIR 2020
- Ronald Ortner: Regret Bounds for Reinforcement Learning via Markov Chain Concentration
AISTATS 2020
- Xuedong Shang, Rianne de Heide, Emilie Kaufmann, Pierre Ménard, Michal Valko: Fixed-Confidence Guarantees for Bayesian Best-Arm Identification
- Julien Seznec, Pierre Ménard, Alessandro Lazaric, Michal Valko: A single algorithm for both restless and rested rotting bandits
ICMA 2020
- Aurélien Garivier, Pierre Ménard, Laurent Rossi: Thresholding Bandit for Dose-ranging: The Impact of Monotonicity
AAAI 2020
- Daniel Furelos-Blanco, Mark Law, Alessandra Russo, Krysia Broda, Anders Jonsson: Induction of Subgoal Automata for Reinforcement Learning
- Javier Segovia-Aguas, Sergio Jiménez, Anders Jonsson: Generalized Planning with Positive and Negative Examples
AIJ 2019
- Javier Segovia-Aguas, Sergio Jiménez, Anders Jonsson: Computing programs for generalized planning using a classical planner
NeurIPS 2019
- Ronald Ortner, Matteo Pirotta, Alessandro Lazaric, Ronan Fruit, Odalric Maillard: Regret Bounds for Learning State Representations in Reinforcement Learning
- Jean-Bastien Grill, Omar Darwiche Domingues, Pierre Ménard, Rémi Munos, Michal Valko: Planning in entropy-regularized Markov decision processes and games
- Rémy Degenne, Wooter Koolen, Pierre Ménard: Non-Asymptotic Pure Exploration by Solving Games
UAI 2019
- Ronald Ortner, Pratik Gajane, Peter Auer: Variational Regret Bounds for Reinforcement Learning
COLT 2019
- Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco: Gaussian process optimization with adaptive sketching: Scalable and no regret
- Peter Auer, Pratik Gajane, Ronald Ortner: Adaptively Tracking the Best Bandit Arm with an Unknown Number of
Distribution Changes - Peter Auer, Yifang Chen, Pratik Gajane, Chung-Wei Lee, Haipeng Luo, Ronald Ortner, Chen-Yu Wei: Achieving Optimal Dynamic Regret for Non-stationary Bandits without Prior Information
ICML 2019
- Pierre Perrault, Vianney Perchet, Michal Valko: Exploiting structure of uncertainty for efficient combinatorial semi-bandits
- Peter Bartlett, Victor Gabillon, Jennifer Healey, Michal Valko: Scale-free adaptive planning for deterministic dynamics with discounted rewards
AutoML@ICML 2019
- Xuedong Shang, Emilie Kaufmann, Michal Valko: A simple dynamic bandit-based algorithm for hyper-parameter tuning
ALT 2019
- Xuedong Shang, Emilie Kaufmann, Michal Valko: General parallel optimization without metric
- Peter L. Bartlett, Victor Gabillon, Michal Valko: A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption
AISTATS 2019
- Julien Seznec, Andrea Locatelli, Alexandra Carpentier, Alessandro Lazaric, Michal Valko: Rotting bandits are no harder than stochastic ones
- Pierre Perrault, Vianney Perchet, Michal Valko: Finding the bandit in a graph: Sequential search-and-stop
- Andrea Locatelli, Alexandra Carpentier, Michal Valko: Active multiple matrix completion with adaptive confidence sets
ICAPS 2019
- Miquel Junyent, Anders Jonsson, Vicenç Gómez: Deep Policies for Width-Based Planning in Pixel Domains
AAAI 2019
- Daniel Furelos-Blanco, Anders Jonsson: Solving Multiagent Planning Problems with Concurrent Conditional Effects
IWSDS 2019
- Eneko Agirre, Anders Jonsson, Anthony Larcher: Framing Lifelong Learning as Autonomous Deployment: Tune Once Live Forever
GRETSI 2019
- Lilian Besson, Emilie Kaufmann: Non-asymptotic analysis of a sequential change-point detection test and applications to non-stationary bandits
JAIR 2018
- Javier Segovia-Aguas, Sergio Jiménez, Anders Jonsson: Computing Hierarchical Finite State Controllers with Classical Planning
PAL 2018
-
Miquel Junyent, Anders Jonsson, Vicenç Gómez: Improving width-based planning with compact policies
EWRL 2018
- Peter Auer, Pratik Gajane, and Ronald Ortner Adaptively Tracking the Best Arm with an Unknown Number of Distribution Changes
- Xuedong Shang, Emilie Kaufmann, Michal Valko: Adaptive black-box optimization got easier: HCT needs only local smoothness
LLARLA 2018 (Best Paper Award)
- Pratik Gajane, Ronald Ortner, and Peter Auer A Sliding-Window Approach for Reinforcement Learning in MDPs with Arbitrarily Changing Rewards and Transitions
COLT 2018
- Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek, Michal Valko: Best of both worlds: Stochastic & adversarial best-arm identification
ECCV 2018
- Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko, Michal Valko: Compressing the input for CNNs with the first-order scattering transform
ICML 2018
-
Daniele Calandriello, Ioannis Koutis, Alessandro Lazaric, Michal Valko: Improved large-scale graph learning through ridge spectral sparsification
-
Ronan Fruit, Matteo Pirotta, Alessandro Lazaric, Ronald Ortner: Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning
NeurIPS 2018
-
Jean-Bastien Grill, Michal Valko, Rémi Munos: Optimistic optimization of a Brownian
-
Emilie Kaufmann, Wouter Koolen, Aurélien Garivier: Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling
The first version of the microgrid benchmark is now available !
Checkout the
- GitHub repository and
- the documentation related