Metraipolis › archive › dc_3edbbc5803f2

ATLAS: Adaptive Topological Learning with Abstract Successors for Continual Learning — arXiv:2608.04334

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04334
License (as archived)
CC0-1.0
Archived
2026-10-31T11:13:40.317Z
SHA-256 of the archived text
eafcd6bb1ba36bf992be03a7a9bd7a6f198381a16bbbbbe5becbc79da382bc4d
Stable URL of this page
https://metraipolis.com/documento/dc_3edbbc5803f2

How to cite

ATLAS: Adaptive Topological Learning with Abstract Successors for Continual Learning — arXiv:2608.04334 — arXiv (en), https://arxiv.org/abs/2608.04334 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3edbbc5803f2 (Metraipolis archive dc_3edbbc5803f2, sha256 eafcd6bb1ba36bf992be03a7a9bd7a6f198381a16bbbbbe5becbc79da382bc4d)
BibTeX
@misc{dc3edbbc5803f2,
  title = {ATLAS: Adaptive Topological Learning with Abstract Successors for Continual Learning — arXiv:2608.04334},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04334},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3edbbc5803f2; sha256 eafcd6bb1ba36bf992be03a7a9bd7a6f198381a16bbbbbe5becbc79da382bc4d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04334. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Contemporary model-free reinforcement learning algorithms can achieve very high performance, but have low sample efficiency and are not robust to changes in the environment. Model-based algorithms have much higher sample efficiency, but still fail when the environment shifts. This paper introduces Adaptive Topological Learning with Abstract Successors (ATLAS) to combat these challenges. ATLAS uses a Grow When Required network with Successor Features in order to achieve high sample efficiency while also robustly tackling catastrophic forgetting. We evaluate ATLAS in spatial navigation tasks, benchmarking its performance against common on-policy and off-policy algorithms. Our empirical results demonstrate that by structurally decoupling transition dynamics from the reward signal, ATLAS achieves near-instantaneous adaptation to new goals and can exhibit positive backward transfer, significantly outperforming baseline methods in non-stationary environments.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04334 — 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 2026-10-31T11:02:13.495Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).