Metraipolis › archive › dc_deb6a046701a

TANDEM: Balancing Centralized and Decentralized Critics to Address the Information Gap in Complex Multi-Agent Environments — arXiv:2610.37592

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37592
License (as archived)
CC0-1.0
Archived
2026-10-28T03:01:08.074Z
SHA-256 of the archived text
364dc8813b9cc23dcfee6c877b2944d7b429b9f05d4b5558e4d2358f293c5528
Stable URL of this page
https://metraipolis.com/documento/dc_deb6a046701a

How to cite

TANDEM: Balancing Centralized and Decentralized Critics to Address the Information Gap in Complex Multi-Agent Environments — arXiv:2610.37592 — arXiv (en), https://arxiv.org/abs/2610.37592 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_deb6a046701a (Metraipolis archive dc_deb6a046701a, sha256 364dc8813b9cc23dcfee6c877b2944d7b429b9f05d4b5558e4d2358f293c5528)
BibTeX
@misc{dcdeb6a046701a,
  title = {TANDEM: Balancing Centralized and Decentralized Critics to Address the Information Gap in Complex Multi-Agent Environments — arXiv:2610.37592},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37592},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_deb6a046701a; sha256 364dc8813b9cc23dcfee6c877b2944d7b429b9f05d4b5558e4d2358f293c5528},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37592. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cooperative multi-agent reinforcement learning under centralized training with decentralized execution (CTDE) shapes decentralized policies with a centralized critic that observes the global state, then removes the critic at execution. The policies are optimized to rely on information they will not have when they act, an information gap between training and execution. It widens under partial observability, observation noise, and openness, where the set of agents and tasks present changes during an episode. Existing methods transfer centralized guidance in one direction only, removing or distilling the critic once, so the policies never rehearse acting without the critic while they can still be corrected. We propose TANDEM, which keeps one centralized critic and reads it two ways at each training step: a centralized read from the global state, and a decentralized read restricted to the information each agent will have at execution. A parameter-free gate compares the two reads for each agent and trains the policy on the decentralized read where they agree, reinstating the centralized read only where the local view is misleading. A shared target pulls the decentralized read toward the centralized one. We formalize the setting as a task- and agent-open decentralized partially observable Markov decision process (TAO-Dec-POMDP) and evaluate TANDEM on three cooperative domains, each isolating one form of the information gap: discovery for partial observability, sampling for observation noise, and openness in wildfire suppression. We compare against six CTDE baselines and ablate the gate and the shared target; the supplementary material holds the full variant sweep, diagnostics, and learning curves. We measure return at execution, once the centralized critic is removed. TANDEM is the best method on eight of the nine setups and never significantly worse than any baseline.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.37592 — 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 2026-10-28T03:01:03.529Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).