higgsfield/RL-Adventure

Issues

• ValueError: too many values to unpack (expected 4)

  #35 opened a year ago by ppangTae
  4

• About Distributional DQN--projection_distribution

  #34 opened 2 years ago by miilue
  1

• Distributional Reinforcement Learning with Quantile Regression

  #3 opened 7 years ago by yydxlv
  6

• Error in projection_distribution (Distributional DQN) ?

  #8 opened 7 years ago by pclucas14
  1

• Error - possibly due to "Variable()" ?

  #22 opened 6 years ago by joleeson
  2

• DQN example: target DQN == behavior DQN (bug? or by design?)

  #32 opened 4 years ago by gordicaleksa
  1

• No prioritized experience replay in rainbow file

  #11 opened 7 years ago by garkavem
  2

• Error in Priority Update for Prioritized Replay

  #13 opened 6 years ago by qfettes
  1

• The update in DQN

  #31 opened 4 years ago by YuxuanXie
  2

• development

  #30 opened 5 years ago by m1996
  0

• RL-Adventure/3.dueling dqn.ipynb missing forward?

  #29 opened 5 years ago by laz8
  0

• batch_size for DQN

  #28 opened 5 years ago by narrowsnap
  0

• ModuleNotFoundError: No module named 'common'

  #27 opened 5 years ago by riccihenrique
  0

• cuda tensor instead of int in 1.dqn

  #10 opened 6 years ago by garkavem
  0

• The atari's state.shape is (210,160,3),and u define the net's in_channel as env.shape[0]

  #23 opened 6 years ago by WonderSeven
  3

• No link found

  #21 opened 6 years ago by ayushmangupta1990
  0

• Environment/dependencies

  #19 opened 6 years ago by janscholten
  2

• Gym env

  #12 opened 6 years ago by ShuvenduRoy
  12

• frame_stack default to False

  #9 opened 7 years ago by lweitkamp
  1

• Licensing

  #7 opened 7 years ago by lweitkamp
  1

• Any possibilities to include A3C implementation?

  #4 opened 7 years ago by hohoCode
  2

• Both David Silver's course and Berkeley's course link to the same URL

  #1 opened 7 years ago by prateekagarwal3
  1