• 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 contribute an implementation of the discrete version of Critic Regularized Regression (CRR) for offline/batch reinforcement learning, which came out around the same time as CQL. Although the original paper only had experiments on continuous control tasks, it was equally applicable to discrete control tasks, on which I was interested in evaluating its performance. I used this repo as reference and tried to follow the contributing guidelines.

A PR will be created soon. Your feedback is highly appreciated.