Metraipolis › archive › dc_62d34c09796e

Cooperative Multi-Agent Reinforcement Learning with Submodular Trajectory Rewards — arXiv:2611.04774

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04774
License (as archived)
CC0-1.0
Archived
2026-11-04T21:35:40.429Z
SHA-256 of the archived text
0025e86face18604e708aa08d35083571a20c817670bb3f72111756d8e5b2ca0
Stable URL of this page
https://metraipolis.com/documento/dc_62d34c09796e

How to cite

Cooperative Multi-Agent Reinforcement Learning with Submodular Trajectory Rewards — arXiv:2611.04774 — arXiv (en), https://arxiv.org/abs/2611.04774 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62d34c09796e (Metraipolis archive dc_62d34c09796e, sha256 0025e86face18604e708aa08d35083571a20c817670bb3f72111756d8e5b2ca0)
BibTeX
@misc{dc62d34c09796e,
  title = {Cooperative Multi-Agent Reinforcement Learning with Submodular Trajectory Rewards — arXiv:2611.04774},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04774},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62d34c09796e; sha256 0025e86face18604e708aa08d35083571a20c817670bb3f72111756d8e5b2ca0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04774. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study cooperative multi-agent reinforcement learning with decoupled dynamics and a monotone submodular reward function over joint trajectories. Due to the non-additive reward, an optimal policy may depend on the history of all agents. This dependence makes exact optimization exponential in the horizon and the number of agents. To overcome this challenge while retaining theoretical guarantees, we introduce pre-window curvature $c_m$, which quantifies how states visited more than $m$ steps earlier reduce current marginal gains. Using this curvature to control the error from restricting the policy of each agent to depend only on its last $m+1$ states, we propose a greedy algorithm that exploits the decoupled dynamics to optimize local policies sequentially. For fixed $m$, the algorithm achieves a $\frac{1-c_m}{2-c_m}$ approximation guarantee up to estimation error, and its computation time is polynomial in the number of agents and the horizon. We recover the known $1/2$-factor approximation for time-additive rewards and obtain an approximation factor no smaller than the known total-curvature bound for a single agent. We formulate multi-agent traffic monitoring as an example of this framework and evaluate our algorithm on it.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.04774 — 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 2026-11-04T21:35:34.334Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).