Solving the 2-level atom non-LTE problem using soft actor-critic reinforcement learning
Lade...
Dateien
Autor:innen
Autor:in (Körperschaft)
Publikationsdatum
2026
Typ der Arbeit
Studiengang
Sammlung
Typ
01A - Beitrag in wissenschaftlicher Zeitschrift
Herausgeber:innen
Herausgeber:in (Körperschaft)
Betreuer:in
Übergeordnetes Werk
RAS Techniques and Instruments
Themenheft
DOI der Originalpublikation
Link
Reihe / Serie
Reihennummer
Jahrgang / Band
5
Ausgabe / Nummer
Seiten / Dauer
Patentnummer
Verlag / Herausgebende Institution
Oxford University Press
Verlagsort / Veranstaltungsort
Auflage
Version
Programmiersprache
Abtretungsempfänger:in
Praxispartner:in/Auftraggeber:in
Zusammenfassung
We present a novel reinforcement learning (RL) approach for solving the classical 2-level atom non-LTE radiative transfer problem by framing it as a control task in which an RL agent learns a depth-dependent source function S(tau) that self-consistently satisfies the equation of statistical equilibrium (SE). The agent’s policy is optimized entirely via reward-based interactions with a radiative transfer engine, without explicit knowledge of the ground truth. This method bypasses the need for constructing approximate lambda operators (Lambda^*) common in accelerated iterative schemes. Additionally, it requires no extensive precomputed labelled data sets to extract a supervisory signal, and avoids backpropagating gradients through the complex RT solver itself. Finally, we show through experiment that a simple feedforward neural network trained greedily cannot solve for SE, possibly due to the moving target nature of the problem. Our Lambda^*-Free method offers potential advantages for complex scenarios (e.g. atmospheres with enhanced velocity fields, multidimensional geometries, or complex microphysics) where Lambda^* construction or solver differentiability is challenging. Additionally, the agent can be incentivized to find more efficient policies by manipulating the discount factor, leading to a reprioritization of immediate rewards. If demonstrated to generalize past its training data, this RL framework could serve as an alternative or accelerated formalism to achieve SE. To the best of our knowledge, this study represents the first application of reinforcement learning in solar physics that directly solves for a fundamental physical constraint.
Schlagwörter
Veranstaltung
Startdatum der Ausstellung
Enddatum der Ausstellung
Startdatum der Konferenz
Enddatum der Konferenz
Datum der letzten Prüfung
ISBN
ISSN
2752-8200
Sprache
Englisch
Während FHNW Zugehörigkeit erstellt
Ja
Zukunftsfelder FHNW
Publikationsstatus
Veröffentlicht
Begutachtung
Peer-Review der ganzen Publikation
Open Access-Status
Gold
Lizenz
Zitation
Panos, B., & Milić, I. (2026). Solving the 2-level atom non-LTE problem using soft actor-critic reinforcement learning. RAS Techniques and Instruments, 5. https://doi.org/10.1093/rasti/rzag005