Line Plot from Scientific Research

Reward trajectories for a circuitous channel. Dreamer v.3 (blue) outperformed the hyperparameter-tuned state-of-the-art PPO (green) across simulation steps. Solid lines show smoothed rewards using an exponentially weighted moving average (EWMA; α = 0.002), and shaded areas represent ±1/3 of the standard deviation around the smoothed data.

DOI