DRL policies equipped with spatial convolution and temporal memory achieve cell coalescence in Rayleigh-Bénard convection at Ra=10,000, reducing Nu by 26% in single-agent setups, and discover adaptive travelling-wave actuation in double-diffusive convection.
, author Constante-Amores, C.R
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.flu-dyn 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep reinforcement learning with spatial and temporal awareness for active boundary control of buoyancy-driven convection
DRL policies equipped with spatial convolution and temporal memory achieve cell coalescence in Rayleigh-Bénard convection at Ra=10,000, reducing Nu by 26% in single-agent setups, and discover adaptive travelling-wave actuation in double-diffusive convection.