This paper is fully reproducible; we provide the protocol that the different modelers used, the data produced from these models, the observed data, and the code to run the analysis that led to the results of the paper, figures, and text. I have not come across any other paper in forestry that is as fully reproducible as our paper, so it might also be a rare example in this field and hopefully a motivation to others to do so. Please notice that we do not provide the models that were used to run the simulations, as these are the results used (or data collection), but we do provide the data resulting from these simulations.
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.
