Metraipolis › archive › dc_f259e5ff157d

Progress Reward Model for Reinforcement Learning via Large Language Models — arXiv:2610.22056

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22056
License (as archived)
CC0-1.0
Archived
2026-10-16T09:05:23.699Z
SHA-256 of the archived text
aae5133f17a8108f046396091e62134edae9cb7fd2b3b7329a0087c7308dabf0
Stable URL of this page
https://metraipolis.com/documento/dc_f259e5ff157d

How to cite

Progress Reward Model for Reinforcement Learning via Large Language Models — arXiv:2610.22056 — arXiv (en), https://arxiv.org/abs/2610.22056 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f259e5ff157d (Metraipolis archive dc_f259e5ff157d, sha256 aae5133f17a8108f046396091e62134edae9cb7fd2b3b7329a0087c7308dabf0)
BibTeX
@misc{dcf259e5ff157d,
  title = {Progress Reward Model for Reinforcement Learning via Large Language Models — arXiv:2610.22056},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22056},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f259e5ff157d; sha256 aae5133f17a8108f046396091e62134edae9cb7fd2b3b7329a0087c7308dabf0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22056. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Traditional reinforcement learning (RL) algorithms face significant limitations in handling long-term tasks with sparse rewards. Recent advancements have leveraged large language models (LLMs) to enhance RL by utilizing their world knowledge for task planning and reward generation. However, planning-based approaches often depend on pre-defined skill libraries and fail to optimize low-level control policies, while reward-based methods require extensive human feedback or exhaustive searching due to the complexity of tasks. In this paper, we propose the Progress Reward Model for RL (PRM4RL), a novel framework that integrates task planning and dense reward to enhance RL. For high-level planning, a complex task is decomposed into a series of simple manageable subtasks, with a subtask-oriented, fine-grained progress function designed to monitor task execution progress. For low-level reward generation, inspired by potential-based reward shaping, we use the progress function to construct a Progress Reward Model (PRM), providing theoretically grounded optimality and convergence guarantees, thereby enabling effective policy optimization. Experimental results on robotics control tasks demonstrate that our approach outperforms both LLM-based planning and reward methods, achieving state-of-the-art performance. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.22056 — 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 2026-10-16T08:44:17.805Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).