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?
Because: - Two fellow PhDs working on different topics have been able to reproduce some figures by following the README instructions and I hope this extends to other people - I've tried to incorporate as many of the best practices as possible to make my code and data open and accessible - I've tried to make sure that my data is exactly reproducible with the specified random seed strategy - the paper suggests a method that should be useful to other researchers in my field, which is not useful unless my results are reproducible
The original data took quite a while to produce for a previous paper, but for this paper, all tables and figures should be exactly reproducible by simply running the jupyter notebook.
