• I have marked all applicable categories:
  • exception-raising bug
  • RL algorithm bug
  • documentation request (i.e. "X is missing from the documentation.")
  • new feature request
• I have visited the source website
• I have searched through the issue tracker for duplicates
• I have mentioned version numbers, operating system and environment, where applicable:

  import tianshou, torch, numpy, sys
  print(tianshou.__version__, torch.__version__, numpy.__version__, sys.version, sys.platform)

I would like to take a stab at implementing IQN and FQF, two distributional RL model with great results on Atari games, following the excellent reference implementations here.

I am almost done with IQN and will submit a PR soon. Before I move on to FQF, I'd highly appreciate your feedback.