This paper proposes a probabilistic planner that can solve goal-conditional tasks such as complex continuous control problems. The approach reaches state-of-the-art performance when compared to current deep reinforcement learning algorithms. However, the method relies on an ensemble of deep generative models and is computationally intensive. It would be interesting to reproduce the results presented in this paper on their robotic manipulation and navigation problems as these are very challenging problems that current reinforcement learning methods cannot easily solve (and when they do, they require a significantly larger number of experiences). Can the results be reproduced out-of-the-box with the provided code?
This was my third attempt at making a paper fully reproducible. To date I it's the most reproducible that I have published. I'm interested to know what stumbling blocks exist that I'm not aware of (aside from needing software like ArcGIS to fully rerun the complete analysis).
