Metraipolis › archive › dc_eace3bd37d80

Critic-Free Policy Iteration for Continuous-Time Zero-Sum Games: A Policy-Space Riccati Approach — arXiv:2609.11564

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11564
License (as archived)
CC0-1.0
Archived
2026-10-16T07:13:43.305Z
SHA-256 of the archived text
9c5e0bfa867610df6708b8508587efc3cfca6ebbffbbc48bbb4bf033cbecfb9a
Stable URL of this page
https://metraipolis.com/documento/dc_eace3bd37d80

How to cite

Critic-Free Policy Iteration for Continuous-Time Zero-Sum Games: A Policy-Space Riccati Approach — arXiv:2609.11564 — arXiv (en), https://arxiv.org/abs/2609.11564 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eace3bd37d80 (Metraipolis archive dc_eace3bd37d80, sha256 9c5e0bfa867610df6708b8508587efc3cfca6ebbffbbc48bbb4bf033cbecfb9a)
BibTeX
@misc{dceace3bd37d80,
  title = {Critic-Free Policy Iteration for Continuous-Time Zero-Sum Games: A Policy-Space Riccati Approach — arXiv:2609.11564},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11564},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eace3bd37d80; sha256 9c5e0bfa867610df6708b8508587efc3cfca6ebbffbbc48bbb4bf033cbecfb9a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11564. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper develops a critic-free policy iteration (PI) method for continuous-time linear zero-sum games. The central idea is to characterize the saddle-point policies directly in the joint policy space, rather than treating the quadratic value matrix as an iterative variable. A policy game Riccati equation (PGRE) is introduced whose unknowns are policy gains only. Its solutions are shown to be in one-to-one correspondence with the symmetric solutions of the game algebraic Riccati equation. Based on a stabilizing anchor, PI is performed directly in the actor space. The actor-space Jacobian is nonsingular at every stabilizing policy, and the resulting policy sequence coincides with that of simultaneous PI. For unknown dynamics, a data-driven algorithm uses a single batch of data and nullspace projection of endpoint increments to eliminate the value matrix, yielding an actor-only regression. A necessary and sufficient rank condition for unique policy recovery is established and shown to be iteration-invariant, demonstrating that critic identifiability is unnecessary. A power systems frequency-regulation example verifies convergence and policy recovery, while scalability tests demonstrate substantial reductions in computational and memory requirements.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-11 in eess.SY).
Categorie arXiv: Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.11564 — 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 2026-10-16T06:56:38.769Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).