Metraipolis › archive › dc_5727340f538f

Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation — arXiv:2609.19414

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19414
License (as archived)
CC0-1.0
Archived
2026-10-10T04:08:37.963Z
SHA-256 of the archived text
96d89baf469d62ddedf83b0bae69a723b4c63342cbd5ef5f2af459ebac6d49c1
Stable URL of this page
https://metraipolis.com/documento/dc_5727340f538f

How to cite

Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation — arXiv:2609.19414 — arXiv (en), https://arxiv.org/abs/2609.19414 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5727340f538f (Metraipolis archive dc_5727340f538f, sha256 96d89baf469d62ddedf83b0bae69a723b4c63342cbd5ef5f2af459ebac6d49c1)
BibTeX
@misc{dc5727340f538f,
  title = {Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation — arXiv:2609.19414},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19414},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5727340f538f; sha256 96d89baf469d62ddedf83b0bae69a723b4c63342cbd5ef5f2af459ebac6d49c1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19414. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Goal-conditioned reinforcement learning aims to learn policies that reach specified goals, but remains challenging in offline settings with sparse rewards and long-horizon dependencies. In such settings, goal-completion information can be temporally distant from the early decisions that enable success, while offline value estimation introduces additional error. We study this issue from a reward-propagation perspective and show, in a stylized delayed-goal setting, how goal-directed value separation can become small relative to local estimation error. Motivated by this analysis, we propose Reward Stimulation Implicit Q-Learning (RSIQL), a simple non-hierarchical method that introduces additional reward signals at progress-making intermediate states in offline trajectories. RSIQL uses an auxiliary goal-conditioned value function to identify intermediate states estimated to make progress toward the goal and applies reward stimulation to provide less-delayed training supervision. Unlike hierarchical methods, RSIQL does not learn a separate high-level subgoal policy. Experiments on D4RL goal-reaching benchmarks and OGBench show that RSIQL improves over goal-conditioned IQL on average and achieves performance competitive with hierarchical offline goal-conditioned methods, while retaining a simple flat policy structure.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.19414 — 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 2026-10-10T03:48:18.256Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).