Projects

Composing RL policies, with formal guarantees

Source code for replicating the experiments presented in our paper Composing Reinforcement Learning Policies, with Formal Guarantees

Florent Delgrange, Guy Avny, Anna Lukina, Christian Schilling, Guillermo A. Pérez, Ann Nowé

Composing RL policies, with formal guarantees

Source code for replicating the expriments presented in the paper The Wasserstein Believer — Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models

WBU

Source code for replicating the expriments presented in the paper Wasserstein Auto-encoded MDPs — Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees

WAE-MDPs

Source code for replicating the expriments presented in the paper Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes