Papers



Submit a Paper!

Browse ReproHack papers

  • PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals

    Authors: Henry Charlesworth and Giovanni Montana
    Submitted by gmontana74      
      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?

  • The Impact of Sound-Bite Journalism on Public Argument

    Authors: Rinke, E. M.
    DOI: 10.1111/jcom.12246
    Submitted by emrinke    

    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.

  • Explicit (but not implicit) environmentalist identity predicts pro-environmental behavior and policy preferences

    Authors: Brick, C., & Lai, C. K.
    DOI: 10.1016/j.jenvp.2018.07.003
    Submitted by hub-admin    
      Mean reproducibility score:   6.0/10   |   Number of reviews:   1
    Why should we attempt to reproduce this paper?

    The results of the individual studies (4) could be interpreted in support for the hypothesis, but the meta-analysis suggested that implicit identification was not a useful predictor overall. This conclusion is an important goalpost for future work.