aviralkumar2907/CQL

Issues

• About hyperparameters for D4RL Kitchen

  #26 opened 6 months ago by YHQpkueecs
  0

• Why substract entropy from Q-values? ("min_q_version == 3")

  #25 opened 9 months ago by ikamensh
  1

• ResolvePackageNotFound

  #20 opened 3 years ago by Shinntarou
  1

• Make checkpoints public

  #24 opened 2 years ago by ezhang7423
  0

• Logsumexp calculation in CQL(H) for continuous action space

  #7 opened 4 years ago by zhihanyang2022
  2

• Why "alpha_prime" and "min_q_weight" are not the same thing when using Lagrange?

  #23 opened 2 years ago by dbsxdbsx
  0

• Potential mismatch between math and code for CQL(rho)

  #8 opened 4 years ago by zhihanyang2022
  2

• `rlkit/torch/sac/cql.py` not found

  #22 opened 3 years ago by anahrendra
  1

• ImportError: cannot import name 'elem_or_tuple_to_numpy' from 'rlkit.torch.core'

  #15 opened 3 years ago by HYDesmondLiu
  3

• About the derivation in paper

  #21 opened 3 years ago by 2019ChenGong
  1

• Error when creating quantile agent for using CQL for Atari

  #1 opened 4 years ago by timo-sievernich
  2

• seed is not actually used in the script

  #14 opened 3 years ago by takuseno
  1

• Unable to open file: 'batch_rl/fixed_replay/configs/quantile_pong.gin'

  #12 opened 4 years ago by 1994cxy
  1

• QF_Loss backprops policy network

  #5 opened 4 years ago by 00schen
  17

• cannot reproduce results of adroit task hammer-cloned, relocate-human and relocate-cloned

  #9 opened 4 years ago by zhanghc12
  1

• Examples for D4RL Experiments

  #11 opened 4 years ago by jiawlu
  0

• code bugs

  #10 opened 4 years ago by rainbow979
  2

• SAC CQL: Potential mismatch between observations and actions fed to the Q network in CQL computation.

  #4 opened 4 years ago by dosssman
  4

• About the readability

  #3 opened 4 years ago by familyld
  2

• Function argument problem about expl_path_collector.collect_new_paths()

  #2 opened 4 years ago by SongyiGao
  1