Metraipolis › archive › dc_9dad41ca41a0
Robust Successor Features — arXiv:2609.31016
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31016
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:13:04.413Z
- SHA-256 of the archived text
dfc41e2c411e9df59dbe9a94458721f5f1fd44c45722548002b0bda8eb03a288- Stable URL of this page
https://metraipolis.com/documento/dc_9dad41ca41a0
How to cite
Robust Successor Features — arXiv:2609.31016 — arXiv (en), https://arxiv.org/abs/2609.31016 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9dad41ca41a0 (Metraipolis archive dc_9dad41ca41a0, sha256 dfc41e2c411e9df59dbe9a94458721f5f1fd44c45722548002b0bda8eb03a288)
BibTeX
@misc{dc9dad41ca41a0,
title = {Robust Successor Features — arXiv:2609.31016},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31016},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9dad41ca41a0; sha256 dfc41e2c411e9df59dbe9a94458721f5f1fd44c45722548002b0bda8eb03a288},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31016. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generalization in Reinforcement Learning (RL) refers to the ability to execute close-to-optimal policies in unseen tasks after the agent has been trained on a different set of tasks. Building on the seminal work of the successor representation and further adaptations with function approximation, Transfer in RL has traditionally focused on generalizing to tasks that only differ in the reward function. A decade after the introduction of the successor representation, Robust RL emerged simultaneously from several articles in the field of operations research. In Robust RL, the transition kernel is unknown, and the goal is to maximize the expected reward under this uncertainty. Our work unifies these two paradigms through robust successor features, which generalize across both the reward function and the transition kernel, under the assumption that tasks are linear Markov Decision Processes. We derive a bound on Generalized Policy Improvement (GPI) that explicitly quantifies how performance degrades with the mismatch between transition kernels, recovering existing successor-feature guarantees when dynamics are shared. Finally, the generalization capabilities of robust successor features are validated on several grid-based benchmarks and compared to previous alternatives that focus solely on either the reward or the transition kernel. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.31016 — 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 2026-10-08T01:43:06.721Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).