keon/deep-q-learning

Issues

• Not learning

  #37 opened 2 years ago by PietroArsi
  0

• ValueError: cannot reshape array of size 2 into shape (1,4)

  #36 opened 2 years ago by akshay-paranjape
  2

• Question: Is this some form of reward engineering?

  #34 opened 4 years ago by WorksWellWithOthers
  1

• Possible incrrection in DQN & DDQN file

  #35 opened 4 years ago by YwEwanHuang
  0

• Making new predictions

  #8 opened 7 years ago by slakkur1
  2

• missing the initialization of target action value and refreshing the Qhat

  #13 opened 7 years ago by fi000
  1

• model save and load does not work

  #16 opened 6 years ago by adibyte95
  8

• should update the weight every time step ?

  #17 opened 6 years ago by fi000
  3

• Would it make sense to restrict the action to what's possible?

  #23 opened 6 years ago by shamoons
  2

• Predict the action for new environment - Inference

  #25 opened 6 years ago by kk2491
  1

• Why are we training the neural network for only 1 epoch

  #31 opened 4 years ago by daysofthunder98
  1

• slower on GPU using tensorflow backend?

  #28 opened 5 years ago by rayset
  1

• IndexError

  #26 opened 5 years ago by aurelieJin
  0

• What is the purpose of "done"?

  #21 opened 6 years ago by shamoons
  2

• ddqn_batch

  #22 opened 6 years ago by Sajjad-moghadam
  0

• Speeding the replay

  #18 opened 6 years ago by marxav
  2

• k frame

  #20 opened 6 years ago by fi000
  0

• memory for state

  #14 opened 6 years ago by fi000
  4

• Saving/reloading weight does not seem to work

  #15 opened 6 years ago by sbaro
  2

• What am I doing wrong?

  #11 opened 7 years ago by mvrozanti
  2

• a hidden bug in your code

  #12 opened 7 years ago by haoran-zhang
  3

• Plot Image

  #9 opened 7 years ago by davsuacar
  2

• add cnn to dqn

  #4 opened 7 years ago by skyer9
  3

• Minor issue with globally scoped variable `env`

  #1 opened 8 years ago by timvieira
  0