While training with static demonstrations has shown some promise, we show that such methods fall short for controlling real GUIs due to their failure to deal with real world stochasticity and non-stationarity not captured in static observational data.

Notice implies Lorenz-dominance.Lor, states rankingisfair

Furthermore, it has also achievedstate-of-the-art performance incombination with recent developments inself-supervised learning methodologies as well [37,62].