-
Authors: Angela I. Renton, Thuy T. Dao, Tom Johnstone, Oren Civier, Ryan P. Sullivan, David J. White, Paris Lyons, Benjamin M. Slade, David F. Abbott, Toluwani J. Amos, Saskia Bollmann, Andy Botting, Megan E. J. Campbell, Jeryn Chang, Thomas G. Close, Monika Dörig, Korbinian Eckstein, Gary F. Egan, Stefanie Evas, Guillaume Flandin, Kelly G. Garner, Marta I. Garrido, Satrajit S. Ghosh, Martin Grignard, Yaroslav O. Halchenko, Anthony J. Hannan, Anibal S. Heinsfeld, Laurentius Huber, Matthew E. Hughes, Jakub R. Kaczmarzyk, Lars Kasper, Levin Kuhlmann, Kexin Lou, Yorguin-Jose Mantilla-Ramos, Jason B. Mattingley, Michael L. Meier, Jo Morris, Akshaiy Narayanan, Franco Pestilli, Aina Puce, Fernanda L. Ribeiro, Nigel C. Rogasch, Chris Rorden, Mark M. Schira, Thomas B. Shaw, Paul F. Sowman, Gershon Spitz, Ashley W. Stewart, Xincheng Ye, Judy D. Zhu, Aswin Narayanan & Steffen Bollmann
Mean reproducibility score:
2.5/10
|
Number of reviews:
2
Why should we attempt to reproduce this paper?
We invested a lot of work to make the analyses from the paper reproducible and we are very curious how the documentation could be improved and if people run into any problems.
-
Authors: Henry Charlesworth and Giovanni Montana
Mean reproducibility score:
10.0/10
|
Number of reviews:
1
Why should we attempt to reproduce this paper?
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?
-
Authors: Rinke, E. M.
Mean reproducibility score:
10.0/10
|
Number of reviews:
1
Why should we attempt to reproduce this paper?
- This paper is a good example of a standard social science study that is (I hope!) fully reproducible, from main analysis, to supplementary analyses and figures.
- I have not yet received any external feedback w.r.t. its reproducibility, so would be interested to see if I have overlooked any gaps in the reproduction workflow that I anticipated.
