openai/random-network-distillation

Issues

• KeyError: 'RCALL_NUM_GPU' ?

  #1 opened a year ago by lhlong
  6

• Wrong PPO Model architecture.

  #26 opened 4 years ago by alirezakazemipour
  2

• How to train agent with only intrinsic reward?

  #27 opened 2 years ago by zijGao
  0

• how to install the 'exptag' package

  #28 opened 3 years ago by jgp-github
  0

• RAM usage problem

  #14 opened 6 years ago by weak-orange-wind
  4

• RewardForwardFilter to compute intrinsic returns for normalize intrinsic reward

  #16 opened 6 years ago by boscotsang
  2

• Is 'news' in your code equivalent to 'dones' in OpenAI Gym?

  #19 opened 4 years ago by weak-orange-wind
  0

• AttributeError: module 'baselines.logger' has no attribute 'ProfileKV'

  #24 opened 4 years ago by fuxianh
  1

• intrinsic reward and extrinsic reward

  #23 opened 4 years ago by rainbow979
  2

• Problems while installing libraries required to run it [mpi4py]

  #22 opened 5 years ago by TheRealRazbi
  0

• bug report: Type error

  #20 opened 5 years ago by ThisIsIsaac
  1

• module 'tensorflow_core._api.v2.nn' has no attribute 'rnn_cell'

  #21 opened 5 years ago by ArtificialIntelligenceRobot
  0

• Saving / Render

  #9 opened 6 years ago by michael20at
  3

• replay

  #7 opened 6 years ago by TheCherry
  3

• Samples of each epoch for optimization were not shuffled

  #17 opened 6 years ago by boscotsang
  0

• why there are two calls to the policy, also where is the non intrinsic characteristic of intrinsic reward?

  #13 opened 6 years ago by mehdimashayekhi
  1

• how to test?

  #12 opened 6 years ago by wangrui1996
  1

• tf.stop_gradient missing?

  #11 opened 6 years ago by navneet-nmk
  3

• VecFrameStack class double

  #10 opened 6 years ago by michael20at
  0

• requirement baseline / MuJoCo

  #6 opened 6 years ago by TheCherry
  1