fast-reinforcement-learning icon indicating copy to clipboard operation
fast-reinforcement-learning copied to clipboard

Published 20 hours ago • verified publisher icon josiahls

DDPG / HER

Open josiahls opened this issue 6 years ago • 0 comments

Discussion Now PER is added, many of the basic DQNs are added. We move to DDPG. Primary goals:

  • [x] DDPG algorithm for continuous envs
  • [x] A way to get DDPG to work in a Discrete env like the maze for debugging.
  • [ ] HER: Hindsight Experience Replay is useful for speeding up learning / improve exploration. This will possibly involve some considerations in regards to data bunches and the MDPSlices.
  • [x] Once these are done, is there a way to unify this under a single fit function?

josiahls avatar Aug 24 '19 22:08 josiahls