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?
The current code is written in Torch, which is no longer actively maintained. Since deep learning in nanophotonics is an area of active interest (e.g. for the design of new metamaterials), it is important to update the code to use a more modern deep learning library such as tensorflow/keras
I tried hard to make this paper as reproducible as possible, but as techniques and dependencies become more complex, it is hard to make it 100% clear. Any form of feedback is more than welcome.