Metraipolis › archive › dc_7629298e8166
UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms — arXiv:2608.15372
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15372
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:13:55.773Z
- SHA-256 of the archived text
f356b677eb1ec052efb667b1a091a84659ec53ac7f1a0e1023c2e4000d5277aa- Stable URL of this page
https://metraipolis.com/documento/dc_7629298e8166
How to cite
UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms — arXiv:2608.15372 — arXiv (en), https://arxiv.org/abs/2608.15372 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7629298e8166 (Metraipolis archive dc_7629298e8166, sha256 f356b677eb1ec052efb667b1a091a84659ec53ac7f1a0e1023c2e4000d5277aa)
BibTeX
@misc{dc7629298e8166,
title = {UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms — arXiv:2608.15372},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15372},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7629298e8166; sha256 f356b677eb1ec052efb667b1a091a84659ec53ac7f1a0e1023c2e4000d5277aa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15372. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study generating game-theoretically optimized Courses of Action (COAs) for a Blue UAS swarm against an adaptive Red adversary in a communication-degraded environment, motivated by (but not derived from) a public U.S. Air Force SBIR solicitation. We propose UC-PSRO (Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum), combining three mechanisms: (i) PSRO self-play, so Blue and Red policies train as approximate best responses to each other rather than one side against a fixed scripted opponent; (ii) FiLM conditioning of the Blue policy on a Commander's-Intent weight vector, sampled from a Dirichlet distribution during training, so one trained policy is re-steerable at execution time without retraining; and (iii) a curriculum annealing communication-graph edge dropout during training, so the swarm learns decentralized, peer-to-peer fallback instead of depending on full connectivity. We evaluate on a synthetic, unclassified stand-in for the solicitation's maritime scenario, with 5 seeds at N=25 Blue agents and a scalability sweep to N=200. We find a genuine trade-off, not a uniform win: the communication-dropout curriculum alone gives the strongest, most robust mission-completion rates of any learned method, improving counter-intuitively as denial increases (35% to 62% success as dropout rises from 0 to 0.75); adding utility-conditioning and PSRO self-play substantially slows convergence within a fixed budget, and we find no reliable exploitability advantage for self-play over a fixed-opponent policy, both statistically indistinguishable from a small, near-zero gap. We report this honestly as a convergence cost not yet offset by a demonstrated robustness benefit, rather than overstating one method as dominant, and provide a fully vectorized, open environment training at N=200 agents in single-digit milliseconds per step on a single consumer GPU. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2608.15372 — 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 2026-10-18T16:29:13.793Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).