Metraipolis › archive › dc_c83dc03fdc76

Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning — arXiv:2610.02847

Source
arXiv
Original
https://arxiv.org/abs/2610.02847
License (as archived)
CC0-1.0
Archived
2026-10-05T22:48:00.631Z
SHA-256 of the archived text
86f4f228600721a6ed864976818a5d8c6219dab30ef089e588bcffabe084eaff
Stable URL of this page
https://metraipolis.com/documento/dc_c83dc03fdc76

How to cite

Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning — arXiv:2610.02847 — arXiv, https://arxiv.org/abs/2610.02847 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c83dc03fdc76 (Metraipolis archive dc_c83dc03fdc76, sha256 86f4f228600721a6ed864976818a5d8c6219dab30ef089e588bcffabe084eaff)
BibTeX
@misc{dcc83dc03fdc76,
  title = {Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning — arXiv:2610.02847},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02847},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c83dc03fdc76; sha256 86f4f228600721a6ed864976818a5d8c6219dab30ef089e588bcffabe084eaff},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02847. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-team multi-agent reinforcement learning studies cooperative systems in which agents may join, leave, or be replaced during an episode. In such settings, the team return changes both because agents choose useful actions and because the active population itself changes. Standard centralized critics and shared advantages often mix these two effects into one scalar credit signal, allowing surviving agents to be rewarded or penalized for exogenous turnover events outside their control. We introduce turnover-orthogonal credit assignment (TOCA), a value decomposition for open teams that separates action effects, pure turnover effects, and action--turnover interactions. Under exogenous turnover, the event-conditioned value admits a centered decomposition whose event-conditioned baseline removes the pure turnover component while preserving credit for actions that make the team robust to future replacements. We instantiate this idea with a permutation-invariant centralized critic over variable-size agent sets and event tokens, and derive both a counterfactual per-agent credit signal and a softly weighted interaction variant, TOCA-$\beta$, for high-variance control environments. Controlled diagnostic experiments show that TOCA improves return over event-aware MAPPO-style critics and that removing interaction credit substantially hurts performance. In a replacement-only Dynamic Spread benchmark, TOCA-$\beta$ achieves the best mean return at high turnover rates and improves over its no-interaction ablation. These results suggest that explicitly separating turnover from action credit is a useful principle for robust learning in dynamic cooperative teams.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.02847 — 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 2026-10-05T22:45:40.631Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).