Metraipolis › archive › dc_4b7e0c8c8564

Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration — arXiv:2611.07066

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07066
License (as archived): CC0-1.0
Archived: 2026-11-06T14:41:24.289Z
SHA-256 of the archived text: 00414aac89c99b43a40398a17598a8486593518c65d4cf8eaeae0d0e868b75e9
Stable URL of this page: https://metraipolis.com/documento/dc_4b7e0c8c8564

How to cite

Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration — arXiv:2611.07066 — arXiv (en), https://arxiv.org/abs/2611.07066 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b7e0c8c8564 (Metraipolis archive dc_4b7e0c8c8564, sha256 00414aac89c99b43a40398a17598a8486593518c65d4cf8eaeae0d0e868b75e9)

BibTeX

@misc{dc4b7e0c8c8564,
  title = {Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration — arXiv:2611.07066},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07066},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b7e0c8c8564; sha256 00414aac89c99b43a40398a17598a8486593518c65d4cf8eaeae0d0e868b75e9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07066. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Discovering cooperative behavior in multi-agent reinforcement learning (MARL) is challenging due to the combinatorial complexity of joint state-action spaces, which hinders the emergence of coordinated behaviors from trial-and-error alone. Intrinsic rewards are often used to aid discovery, but naively combining them with team objectives can distort the learning signal, compromising task performance. In this paper, we propose EFXPLORER, a constrained exploration framework that maximizes exploration objectives subject to a constraint that preserves established task performance. We solve the resulting problem using an epigraph reformulation that introduces adaptive exploration budgets. This approach separates intrinsic rewards from task objectives and regulates exploration through task feasibility. To further encourage diverse and temporally extended exploration, we incorporate a successor distance-based intrinsic reward that captures long-horizon dependencies. Empirically, our method outperforms strong baselines and induces novel cooperative strategies across SMAX, VMAS, and MPE benchmark suites.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.07066 — 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 2026-11-06T14:18:27.665Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).