There is a numerical benchmark reported in Fig. 4 with absolute runtimes and memory usages that can directly be reproduced with the provided source code. The benchmark was performed on the author's computer, and since numerical performance and parallel scaling can be somewhat hardware-dependent, it would be of interest to see whether a performance that is comparable to the one reported in the paper can be reproduced by others on their own computers in practice. The benchmark simulates a growing tissue from one to 10,000 cells in just ten minutes, so this offers an easy entry point into tissue modeling and simulation. No input data is needed to reproduce the output. The program has no dependencies.
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?
