However, in practice, the environment is typically time-varying and nonstationary .

And model misspecification has not been considered as an unresolved issue [36,38,53,54].

Aprominent challenge is to train an agent capable of generalising to new environments attest time, rather than one that simply memorises trajectories and visual details observed during training. We propose a new learning strategy that learns both from observations and generatedcounterfactual environments.

In general, interventional data, i.e., data collected after a perturbation in