Metraipolis › archive › dc_1f148f400bcb
Differentiating Bisimulation Metrics: A Framework for Parametric Markov Chain Fitting via Bicausal Optimal Transport — arXiv:2609.37239
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37239
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:30:52.952Z
- SHA-256 of the archived text
23ae7736de3edba1fb8b3e3eb969b4bc7c7759df151484fb90c974a95fd201e8- Stable URL of this page
https://metraipolis.com/documento/dc_1f148f400bcb
How to cite
Differentiating Bisimulation Metrics: A Framework for Parametric Markov Chain Fitting via Bicausal Optimal Transport — arXiv:2609.37239 — arXiv (en), https://arxiv.org/abs/2609.37239 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1f148f400bcb (Metraipolis archive dc_1f148f400bcb, sha256 23ae7736de3edba1fb8b3e3eb969b4bc7c7759df151484fb90c974a95fd201e8)
BibTeX
@misc{dc1f148f400bcb,
title = {Differentiating Bisimulation Metrics: A Framework for Parametric Markov Chain Fitting via Bicausal Optimal Transport — arXiv:2609.37239},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37239},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1f148f400bcb; sha256 23ae7736de3edba1fb8b3e3eb969b4bc7c7759df151484fb90c974a95fd201e8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37239. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many problems in sequential decision-making, such as imitation learning from observations, state-space compression, world-model learning, and sim-to-real transfer, can be reduced to learning a model such that a notion of distance with respect to the target process is minimized. We consider this general framework and consider the bisimulation metric, equivalently Bicausal Optimal Transport (BOT), as the notion of distance to minimize. We show that BOT, since it can be formulated as a linear program (LP), is differentiable with respect to the model dynamics. We then derive an exact closed-form gradient via the envelope theorem applied to the LP saddle point. The result is a general algorithm, Differentiable Bicausal Optimal Transport (D-BOT), that can be applied to each of the problems above. The proposed algorithm learns the best model by alternating between distance computation and gradient steps. We apply D-BOT for three different settings: state-space compression, parametric model learning, and imitation learning from observations (ILfO). We show empirical results that confirm the viability of all three instantiations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.37239 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T16:59:48.308Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).