Life is Random, Time is Not: Markov Decision Processes with Window Objectives von Thomas Brihaye, Florent Delgrange, Youssouf Oualhadj, Mickael Randour

Volltext

A framework for flexibly guiding learning agents von Elbarbari, Mahmoud, Delgrange, Florent, Vervlimmeren, Ivo, Efthymiadis, Kyriakos, Vanderborght, Bram, Nowé, Ann

Volltext

Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees von Delgrange, Florent, Nowé, Ann, Pérez, Guillermo A

Volltext bestellen

Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report) von Delgrange, Florent, Nowé, Ann, Pérez, Guillermo A

Volltext bestellen

Synthesis of Hierarchical Controllers Based on Deep Reinforcement Learning Policies von Delgrange, Florent, Avni, Guy, Lukina, Anna, Schilling, Christian, Nowé, Ann, Pérez, Guillermo A

Volltext bestellen

The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models von Avalos, Raphael, Delgrange, Florent, Nowé, Ann, Pérez, Guillermo A, Roijers, Diederik M

Volltext bestellen

Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees von Delgrange, Florent, Nowé, Ann, Pérez, Guillermo A

Volltext

Life is Random, Time is Not: Markov Decision Processes with Window Objectives von Brihaye, Thomas, Delgrange, Florent, Oualhadj, Youssouf, Randour, Mickael

Volltext

Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report) von Delgrange, Florent, Nowé, Ann, Pérez, Guillermo A

Volltext

Simple Strategies in Multi-Objective MDPs (Technical Report) von Delgrange, Florent, Katoen, Joost-Pieter, Quatmann, Tim, Randour, Mickael

Volltext bestellen

Synthesis of Hierarchical Controllers Based on Deep Reinforcement Learning Policies von Delgrange, Florent, Avni, Guy, Lukina, Anna, Schilling, Christian, Nowé, Ann, Pérez, Guillermo A

Volltext

The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models von Avalos, Raphael, Delgrange, Florent, Nowé, Ann, Pérez, Guillermo A, Roijers, Diederik M

Volltext

Simple Strategies in Multi-Objective MDPs (Technical Report) von Delgrange, Florent, Joost-Pieter Katoen, Quatmann, Tim, Randour, Mickael

Volltext