I finished working on a new algorithm in Reinforcement Learning, I need to compare it to some well-known algorithms. That's why I need to know the step-by-step procedures that RL researchers usually take in order to get their results and compare them to other papers' results. (e.g. running the algorithm multiple times with different random seeds, saving results to .csv files, plotting).

Anyone can help?

(I am working on Pytorch, PyBullet Environments.)

  • 1
    $\begingroup$ I am not sure exactly what you are looking for. To compare your procedures with well known paper, maybe use paperswithcode.com $\endgroup$
    – jgauth
    May 11, 2020 at 16:30
  • $\begingroup$ This question is indeed a little bit unclear. Are you looking for methods of how RL researchers do research and write their research papers? $\endgroup$
    – nbro
    May 11, 2020 at 17:40


Browse other questions tagged .