Metraipolis › archive › dc_aa669737fa32

SUN: Reaching for Novelty in Reinforcement Learning — arXiv:2609.08642

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08642
License (as archived)
CC0-1.0
Archived
2026-10-16T13:58:21.405Z
SHA-256 of the archived text
34a20414d9ba5858e7a1d8e62aa5ac584839a688b3938209d77950ce2b418cee
Stable URL of this page
https://metraipolis.com/documento/dc_aa669737fa32

How to cite

SUN: Reaching for Novelty in Reinforcement Learning — arXiv:2609.08642 — arXiv (en), https://arxiv.org/abs/2609.08642 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa669737fa32 (Metraipolis archive dc_aa669737fa32, sha256 34a20414d9ba5858e7a1d8e62aa5ac584839a688b3938209d77950ce2b418cee)
BibTeX
@misc{dcaa669737fa32,
  title = {SUN: Reaching for Novelty in Reinforcement Learning — arXiv:2609.08642},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08642},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa669737fa32; sha256 34a20414d9ba5858e7a1d8e62aa5ac584839a688b3938209d77950ce2b418cee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08642. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Exploration in reinforcement learning (RL) remains a fundamental challenge. Recent goal-conditioned RL strategies (which select goals to encourage broader state coverage) have shown promising results, but none scores a goal by novelty and reachability jointly: the two signals are traded off by hand, applied in sequence, or one is neglected outright. In this paper, we introduce a reachability-aware goal-selection framework that explicitly integrates these two aspects, and that can be seamlessly incorporated into any off-policy RL algorithm. To this aim, we propose SUccessor-to-Novelty (SUN), an indicator derived from successor value functions to identify goals that are both novel and reachable. We prove that SUN is the value of a count-scaled goal-reaching reward, bounds short-horizon hitting probabilities, and rejects unreachable goals. We further present an adaptive goal-selection strategy that leverages these properties, along with an accurate yet lightweight pseudocount to avoid the overhead of classic methods. We back up all our claims with thorough benchmarks: SUN consistently outperforms state-of-the-art methods in standard and novel environments with unreachable or hard-to-reach states, irreversible transitions, obstacles, mazes, and unbounded spaces. Code at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.08642 — 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 2026-10-16T13:39:43.056Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).