I tried hard to make it reproducible, so hopefully this paper can serve as an example on how reproducibility can be achieved. I think that being reproducible with only few commands to type in a terminal is quite an achievment. At least in my field, where I usually see code published along with paper, but with almost no documentation on how to rerun it.
The direct numerical simulations (DNS) for this paper were conducted using Basilisk (http://basilisk.fr/). As Basilisk is a free software program written in C, it can be readily installed on any Linux machine, and it should be straightforward to then run the driver code to re-produce the DNS from this paper. Given this, the numerical solutions presented in this paper are a result of many high-fidelity simulations, which each took approximately 24 CPU hours running between 4 to 8 cores. Hence the difficulty in reproducing the results should mainly be in the amount of computational resources it would take, so HPC resources will be required. The DNS in this paper were used to validate the presented analytical solutions, as well as extend the results to a longer timescale. Reproducing these numerical results will build confidence in these results, ensuring that they are independent of the system architecture they were produced on.
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
This paper shows a fun and interesting simulation result. I find it (of course) very important that our results are reproducible. In this paper, however, we did not include the exact code for these specific simulations, but the results should be reproducible using the code of our previous paper in PLOS Computational Biology (Van Oers, Rens et al. https://doi.org/10.1371/journal.pcbi.1003774). I am genuinely curious to see if there is sufficient information for the Biophys J paper or if we should have done better. Other people have already successfully built upon the 2014 (PLOS) paper using our code; see e.g., https://journals.aps.org/pre/abstract/10.1103/PhysRevE.97.012408 and https://doi.org/10.1101/701037).
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.
