Metraipolis › archive › dc_ae5ea47e1a45

Reward Machines for Signal Temporal Logic — arXiv:2608.13625

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13625
License (as archived)
CC0-1.0
Archived
2026-10-19T02:20:20.598Z
SHA-256 of the archived text
d32d161e34151b0e26ec0f15744577c3797e529adaeec4ffaf777f9097b98a89
Stable URL of this page
https://metraipolis.com/documento/dc_ae5ea47e1a45

How to cite

Reward Machines for Signal Temporal Logic — arXiv:2608.13625 — arXiv (en), https://arxiv.org/abs/2608.13625 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae5ea47e1a45 (Metraipolis archive dc_ae5ea47e1a45, sha256 d32d161e34151b0e26ec0f15744577c3797e529adaeec4ffaf777f9097b98a89)
BibTeX
@misc{dcae5ea47e1a45,
  title = {Reward Machines for Signal Temporal Logic — arXiv:2608.13625},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13625},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae5ea47e1a45; sha256 d32d161e34151b0e26ec0f15744577c3797e529adaeec4ffaf777f9097b98a89},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13625. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-valued observations, along with a quantitative robustness score for monitoring satisfaction. Control synthesis from STL specifications is of interest since manual controller design becomes infeasible as real-world systems grow in complexity. Moreover, many modern autonomous and AI-enabled systems lack accurate and complete system models, which makes optimization-based synthesis approaches unsuitable and motivates learning-based control. Prior work uses STL robustness scores as rewards in reinforcement learning (RL) to obtain control policies satisfying given specifications; however, robustness depends on execution history, leading to intractable state space expansion for general long-horizon specifications with arbitrarily nested temporal operators. This work introduces a novel automata-based approach that provides an efficient memory mechanism and associated Markovian rewards suitable for RL frameworks. Our approach constructs a timed alternating automaton from the given STL specifications, augments the state space with automaton locations and clock valuations, and derives rewards from the automaton acceptance condition. We empirically demonstrate that our approach learns policies that achieve higher robustness scores and satisfaction rates than those learned by existing approaches using robustness-based rewards.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.13625 — 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 2026-10-19T02:02:02.729Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).