Metraipolis › archive › dc_470ff347fc41

Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games — arXiv:2610.11663

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.11663
License (as archived): CC0-1.0
Archived: 2026-10-09T05:48:15.744Z
SHA-256 of the archived text: f7276ee34094a4253b72bb06c4adc54f5c268faa0bf5c78cb08427164b18dc1f
Stable URL of this page: https://metraipolis.com/documento/dc_470ff347fc41

How to cite

Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games — arXiv:2610.11663 — arXiv (en), https://arxiv.org/abs/2610.11663 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_470ff347fc41 (Metraipolis archive dc_470ff347fc41, sha256 f7276ee34094a4253b72bb06c4adc54f5c268faa0bf5c78cb08427164b18dc1f)

BibTeX

@misc{dc470ff347fc41,
  title = {Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games — arXiv:2610.11663},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11663},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_470ff347fc41; sha256 f7276ee34094a4253b72bb06c4adc54f5c268faa0bf5c78cb08427164b18dc1f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11663. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep reinforcement learning agents reach strong performance in real-time strategy games but can be brittle against opponents outside their training distribution. Separating strategic command selection from learned unit control allows different strategies to be selected for different opponents while reusing the same execution policy. This requires an executor that can follow different commands and measurable criteria for assessing whether it does so. We introduce a constrained command-conditioned Proximal Policy Optimization (PPO) policy, the executor, for MicroRTS, a real-time strategy environment. Discrete commands specify strategic objectives and behavioral requirements for economy, army composition, military posture, and worker policy over multiple environment steps; the executor determines the unit-level actions used to fulfill them. A Thompson-sampling bandit acts as the strategist, selecting command tuples from an estimate of the opponent's strategy built from in-game observations rather than opponent identity. In a controlled comparison with a flat PPO baseline trained with the same architecture, budget, curriculum and self-play league, the strategist-executor system wins significantly more often against three of the four strongest opponents on a training map, including the two strongest held-out ones (0.55 to 0.97 and 0.01 to 0.34), with no significant difference against the others.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.11663 — 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 2026-10-09T05:47:00.891Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).