Generative Modeling | Florent Delgrangehttps://delgrange.me/category/generative-modeling/Generative ModelingWowchemy (https://wowchemy.com)en-usFri, 23 May 2025 00:00:00 +0000https://delgrange.me/media/icon_hu55be7e40e5cc7772513f5d192dadedff_14178_512x512_fill_lanczos_center_3.pngGenerative Modelinghttps://delgrange.me/category/generative-modeling/Composing Reinforcement Learning Policies, with Formal Guaranteeshttps://delgrange.me/publication/delgrange-2025-synthesis/Fri, 23 May 2025 00:00:00 +0000https://delgrange.me/publication/delgrange-2025-synthesis/<p>This work received the <strong>Best Poster Award</strong> at <a href="https://www.benerl.org/workshop/2025-eindhoven#h.1145sba7zrwi" target="_blank" rel="noopener">BeNeRL 2025</a>.</p>The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Modelshttps://delgrange.me/publication/https-doi-org-10-48550-arxiv-2303-03284/Wed, 29 May 2024 00:00:00 +0000https://delgrange.me/publication/https-doi-org-10-48550-arxiv-2303-03284/WAE-PCN: Wasserstein-autoencoded Pareto Conditioned Networkshttps://delgrange.me/publication/wae-pcn/Mon, 29 May 2023 00:00:00 +0000https://delgrange.me/publication/wae-pcn/Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guaranteeshttps://delgrange.me/publication/delgrange-2023-wasserstein/Sun, 01 Jan 2023 00:00:00 +0000https://delgrange.me/publication/delgrange-2023-wasserstein/Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processeshttps://delgrange.me/publication/dblp-journalscorrabs-2112-09655/Tue, 28 Jun 2022 00:00:00 +0000https://delgrange.me/publication/dblp-journalscorrabs-2112-09655/