Closure Discovery for Coarse-Grained Partial Differential Equations using Multi-Agent Reinforcement Learning

Reliable predictions of critical phenomena, such as weather, wildfires and epidemics are often founded on models described by Partial Differential Equations (PDEs). However, simulations that capture the full range of spatio-temporal scales in such PDEs are often prohibitively expensive. Consequently, coarse-grained simulations that employ heuristics and empirical closure terms are frequently utilized as an alternative. We propose a novel and systematic approach for identifying closures in under-resolved PDEs using Multi-Agent Reinforcement Learning (MARL). The MARL formulation incorporates inductive bias and …

agent cs.lg cs.ma differential discovery epidemics heuristics multi-agent physics.comp-ph predictions reinforcement reinforcement learning simulations temporal terms weather wildfires