haarnoja/sac

Issues

• Why sac is off policy?

  #36 opened 2 years ago by MohammadAsadolahi
  0

• TD3 vs SAC

  #35 opened 3 years ago by HYDesmondLiu
  0

• DIAYN result reproduction & additional charts

  #34 opened 3 years ago by bozic-djordje
  0

• potential recursive call in get_actions(self, observations) from sac/policies/gmm.py

  #33 opened 4 years ago by fangqyi
  1

• Double Q for DIAYN

  #32 opened 4 years ago by josiahls
  5

• The comprehension of the policy limitations in SAC

  #31 opened 4 years ago by OrionZou
  1

• NNDiscriminatorFunction error

  #7 opened 6 years ago by srama2512
  6

• About markovian environments

  #30 opened 4 years ago by shanlior
  4

• maximization bias

  #29 opened 4 years ago by mikelty
  1

• Inquiries about the benchmark results

  #28 opened 5 years ago by anahrendra
  1

• a mathematical problem ..

  #27 opened 5 years ago by bofen97
  1

• what is "sandbox"

  #26 opened 5 years ago by zienn
  2

• Docker Image won't create due to conda's environment.yml inconsistencies

  #25 opened 5 years ago by rock-it-with-asher
  0

• How to run DIAYN on softlearning repo ?

  #24 opened 6 years ago by ZhuFengdaaa
  2

• SAC and cross-maze ant

  #8 opened 6 years ago by acohen13
  2

• Reward scale

  #23 opened 6 years ago by lgvaz
  1

• for discrete env

  #21 opened 6 years ago by ccplxx
  3

• could there be a problem with the initialization of GaussianPolicy ?

  #19 opened 6 years ago by guyk1971
  0

• Stupid issue

  #18 opened 6 years ago
  1

• Dependency issue while building docker

  #16 opened 6 years ago by m4x1mus
  0

• paper/code conflict: using minimum Q in policy gradient

  #14 opened 6 years ago by jpreiss
  1

• Hyperparameter Advice

  #12 opened 6 years ago by Random-Word
  2

• TypeError: __init__() got an unexpected keyword argument 'event_ndims'

  #11 opened 6 years ago by cdevin
  3

• is chainer dep necessary?

  #2 opened 6 years ago by vlad17
  2

• Network weights becoming NaN

  #9 opened 6 years ago by acohen13
  1

• Sparse Reward Environments

  #5 opened 7 years ago by bhairavmehta95
  3

• Replication of Paper

  #4 opened 7 years ago by bhairavmehta95
  1