/D4PG-ray

Distributed PyTorch implementation of D4PG with ray. Using a SOTA IQN Critic instead of C51. Implementation includes also the extensions Munchausen RL and D2RL which can be added to D4PG to improve its performance.

Primary LanguagePython

D4PG-ray

TODO:

  • Clear / clean code
  • Do testruns for LunarLander // Pendulum
  • Make comparisons of all features
  • Make Readme
  • Add PER