Goal-oriented exploration for reinforcement learning von Tarbouriech, Jean

Volltext bestellen

Probabilistic Inference in Reinforcement Learning Done Right von Tarbouriech, Jean, Lattimore, Tor, O'Donoghue, Brendan

Volltext bestellen

Active Exploration in Markov Decision Processes von Tarbouriech, Jean, Lazaric, Alessandro

Volltext bestellen

Probabilistic Inference in Reinforcement Learning Done Right von Tarbouriech, Jean, Lattimore, Tor, O'Donoghue, Brendan

Volltext

Improved Sample Complexity for Incremental Autonomous Exploration in MDPs von Tarbouriech, Jean, Pirotta, Matteo, Valko, Michal, Lazaric, Alessandro

Volltext bestellen

A Provably Efficient Sample Collection Strategy for Reinforcement Learning von Tarbouriech, Jean, Pirotta, Matteo, Valko, Michal, Lazaric, Alessandro

Volltext bestellen

Adaptive Multi-Goal Exploration von Tarbouriech, Jean, Domingues, Omar Darwiche, Ménard, Pierre, Pirotta, Matteo, Valko, Michal, Lazaric, Alessandro

Volltext bestellen

Active Model Estimation in Markov Decision Processes von Tarbouriech, Jean, Shekhar, Shubhanshu, Pirotta, Matteo, Ghavamzadeh, Mohammad, Lazaric, Alessandro

Volltext bestellen

Active Exploration in Markov Decision Processes von Tarbouriech, Jean, Lazaric, Alessandro

Volltext

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching von Kamienny, Pierre-Alexandre, Tarbouriech, Jean, Lamprier, Sylvain, Lazaric, Alessandro, Denoyer, Ludovic

Volltext bestellen

No-Regret Exploration in Goal-Oriented Reinforcement Learning von Tarbouriech, Jean, Garcelon, Evrard, Valko, Michal, Pirotta, Matteo, Lazaric, Alessandro

Volltext bestellen

Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret von Tarbouriech, Jean, Zhou, Runlong, Du, Simon S, Pirotta, Matteo, Valko, Michal, Lazaric, Alessandro

Volltext bestellen

Adversarial Attacks on Linear Contextual Bandits von Garcelon, Evrard, Roziere, Baptiste, Meunier, Laurent, Tarbouriech, Jean, Teytaud, Olivier, Lazaric, Alessandro, Pirotta, Matteo

Volltext bestellen

A Provably Efficient Sample Collection Strategy for Reinforcement Learning von Tarbouriech, Jean, Pirotta, Matteo, Valko, Michal, Lazaric, Alessandro

Volltext

Improved Sample Complexity for Incremental Autonomous Exploration in MDPs von Tarbouriech, Jean, Pirotta, Matteo, Valko, Michal, Lazaric, Alessandro

Volltext

No-Regret Exploration in Goal-Oriented Reinforcement Learning von Tarbouriech, Jean, Evrard Garcelon, Valko, Michal, Pirotta, Matteo, Lazaric, Alessandro

Volltext

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching von Pierre-Alexandre Kamienny, Tarbouriech, Jean, Lamprier, Sylvain, Lazaric, Alessandro, Denoyer, Ludovic

Volltext

Active Model Estimation in Markov Decision Processes von Tarbouriech, Jean, Shekhar, Shubhanshu, Pirotta, Matteo, Ghavamzadeh, Mohammad, Lazaric, Alessandro

Volltext

Adaptive Multi-Goal Exploration von Tarbouriech, Jean, Omar Darwiche Domingues, Ménard, Pierre, Pirotta, Matteo, Valko, Michal, Lazaric, Alessandro

Volltext

Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret von Tarbouriech, Jean, Zhou, Runlong, Du, Simon S, Pirotta, Matteo, Valko, Michal, Lazaric, Alessandro

Volltext