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?
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.
I guess it could be a cool learning experience. The paper is written with knitr, uses a seed, is part of the R package it describes, was openly written using version control (SVN, R-Forge) and is available in an open access journal (@up_jors).
