/redo

ReDo: The Dormant Neuron Phenomenon in Deep Reinforcement Learning (pytorch)

Primary LanguagePython

Recycling dormant neurons

NOTE: This implementation is not correct as of now. I plan to fix it in the coming week!

TODOS:

  • Fix bug in recycling/tracking for tau > 0.
  • Fix the conda env (einops is missing)
  • Add figures from the paper
  • Write a proper README