Operator-Guided Invariance Learning for Continuous Reinforcement Learning

ArXi:2605.06500v1 Announce Type: new Reinforcement learning (RL) with continuous time and state/action spaces is often data-intensive and brittle under nuisance variability and shift, motivating methods that exploit value-preserving structures to stabilize and improve learning. Most existing approaches focus on special cases, such as prescribed symmetries and exact equivariance, without addressing how to discover general structures that require nonlinear operators to transform and map between continuous state/action systems with isomorphic value functions.