Activating formal verification of deep reinforcement learning policies by model checking bisimilar latent space models

Florent Delgrange

Faculteit van de Wetenschappen

Onderzoeksoutput: PhD Thesis

138 Downloads (Pure)

3 Conference paper
2 Unpublished abstract

3 resultaten

Filter

2024
The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
Avalos, R., Delgrange, F., Nowé, A., Pérez, G. A. & Roijers, D. M., 7 mei 2024, The Twelfth International Conference on Learning Representations: ICLR 2024. OpenReview.net, 9 blz.
Onderzoeksoutput: Conference paper › Research

Open Access
Bestand
15 Downloads (Pure)
2023
Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees
Delgrange, F., Nowe, A. & Pérez, G. A., 1 feb 2023, The Eleventh International Conference on Learning Representations: ICLR 2023. Kigali, Rwanda: OpenReview.net, Vol. 11. blz. 1-30 30 blz. 4010
Onderzoeksoutput: Conference paper › Research

Open Access
Bestand
1 Citaat (Scopus)

81 Downloads (Pure)
2022
Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes
Delgrange, F., Nowé, A. & Pérez, G. A., 28 jun 2022, Proceedings of the AAAI Conference on Artificial Intelligence: Vol. 36 No. 6: AAAI-22 Technical Tracks 6. First redactie Palo Alto, California USA: AAAI Press, Vol. 36. blz. 6497-6505 9 blz. (Proceedings of the AAAI Conference on Artificial Intelligence; vol. 36, nr. 6).
Onderzoeksoutput: Conference paper › Research

Open Access
Bestand
4 Citaten (Scopus)

41 Downloads (Pure)