godka/Pensieve-PPO

Issues

• Way to replicate baseline results for different data sets

  #26 opened 2 years ago by kaczor3213
  0

• What do the dimensions of the state returned by the environment mean? What are the corresponding parameters in the paper?

  #21 opened 3 years ago by 945716994
  1

• 有最新关于这方面的进展的Paper吗？我看Pensieve论文里说，没有多少改进空间了。

  #20 opened 3 years ago by 945716994
  1

• Does it run on Windows?

  #19 opened 3 years ago by 945716994
  1

• a2c vs ppo NN architecture

  #13 opened 3 years ago by ahmad-hl
  4

• A question about the comparing function "r" between new and old policies

  #16 opened 3 years ago by youngboy52
  1

• How to improve exploration?

  #11 opened 3 years ago by ahmad-hl
  2

• Monitor cross-validation curve

  #8 opened 3 years ago by ahmad-hl
  5

• SAC import error

  #9 opened 3 years ago by ahmad-hl
  2

• setting entropy to TD_loss summary vars

  #10 opened 3 years ago by ahmad-hl
  3

• a question about compute_v

  #4 opened 4 years ago by linnaeushuang
  8

• Is this project based on python3？and which version of tf2.x?

  #6 opened 4 years ago by youngboy52
  6

• The time to train the model

  #7 opened 4 years ago by SoonyangZhang
  1

• Training with Multiple videos with random number of bitrates masked.

  #3 opened 4 years ago by manojsoni2
  5

• TQL

  #1 opened 5 years ago by xiaxiaxiahhh
  1