simoninithomas/Deep_reinforcement_learning_Course

Issues

• Stuck at Local Minimum in PPO with CarRacing-v2 Environment

  #87 opened 4 days ago by bantu-4879
  0

• No romfiles found for game: SpaceInvaders-Atari2600

  #64 opened 5 years ago
  4

• INPUT and OUTPUT

  #86 opened a year ago by luzi560
  0

• who do struggle with tf.nn.softmax_cross_entropy_with_logits_v2 in Cartpole REINFORCE Monte Carlo Policy Gradients

  #85 opened a year ago by gekator
  0

• Dose this code "Policy Gradient/Doom" really work?

  #84 opened 2 years ago by andersonhusky
  0

• bug in space invaders

  #83 opened 3 years ago by zzlqwq
  0

• ValueError: ('Cannot warp empty image with dimensions', (0, 24))

  #77 opened 4 years ago by EXJUSTICE
  2

• DQN with Doom - Agent Performance

  #82 opened 4 years ago by HWerneck
  0

• rewards_list variable in Deep Q Learning in Space Invaders

  #71 opened 4 years ago by crazylazylife
  2

• Link to "Q* Learning with FrozenLake 🕹️⛄_unslippery" is broken

  #79 opened 4 years ago by goelakash
  0

• DQN Atari Space Invaders issue

  #52 opened 5 years ago by barryallenlord
  2

• Performance of RND at Montezuma's Revenge

  #78 opened 4 years ago by kimbring2
  0

• Deep Q-Learning, Spaceinvaders, retro-gym

  #31 opened 5 years ago by Yaroina
  2

• retro has no attribute make

  #36 opened 5 years ago by HsnAtwi
  5

• [Deep Q Learning with Doom] ValueError: Cannot feed value of shape (64, 84, 84, 4, 260) for Tensor 'DQNetwork/inputs:0', which has shape '(?, 84, 84, 4)'

  #40 opened 5 years ago by tyseng92
  5

• Question for deep-q learning Algo

  #74 opened 4 years ago by rajanlagah
  0

• Requirements .txt needed

  #73 opened 4 years ago by piEsposito
  2

• Preprocessing returns a black screen

  #76 opened 4 years ago by EXJUSTICE
  1

• Deep Q Learning - Doom

  #32 opened 5 years ago by aneekdas96
  4

• No issue, just praise and a suggestion

  #72 opened 4 years ago by Tylersuard
  0

• Killed - Atari Space Invaders

  #59 opened 5 years ago by riccihenrique
  1

• bug in space invaders

  #68 opened 5 years ago by yonigottesman
  0

• Can anyone explain Why we have self.Q = tf.reduce_sum(tf.multiply(self.output, self.actions_), axis=1) in Deep Q learning with Doom.ipynb

  #65 opened 5 years ago by ParmpalGill
  1

• Getting error on 2 seperate cells with instantiating memory and running tensorboard with Doom.

  #66 opened 5 years ago by GhettoBurger996
  3

• Deep Q learning: Algorithm

  #67 opened 5 years ago by wailker3
  0

• Memory Issues (DQN and DDQN)

  #57 opened 5 years ago by Dewald928
  3

• AttributeError: spec missing in TimeLimit wrapper

  #63 opened 5 years ago by kmcnayr
  1

• Process got killed after Episode 17

  #62 opened 5 years ago by ravishk1
  1

• Deep Q Learning Spaceinvaders

  #33 opened 5 years ago by noobmaster29
  15

• Why we have self.Q = tf.reduce_sum(tf.multiply(self.output, self.actions_), axis=1) ?

  #61 opened 5 years ago by Meur-sault
  0

• The old and the new model is effectively the same?

  #60 opened 5 years ago by yuan1202
  0

• Something about saving models

  #58 opened 5 years ago by MeredithChai
  0

• Possible mistake in Deep Q Learning Space Invaders notebook

  #51 opened 5 years ago by karolisjan
  1

• question on checkpoint restart

  #56 opened 5 years ago by rnunziata
  0

• Breakout in RND

  #55 opened 5 years ago by rnunziata
  0

• reset not called in MaxAndSkipEnv

  #54 opened 5 years ago by rnunziata
  0

• System hangs after running a while

  #53 opened 5 years ago by rnunziata
  1

• memory leak

  #50 opened 5 years ago by dxls168
  0

• Sonic A2C not working for Pong

  #48 opened 5 years ago by slerman12
  5

• Logging for graphing

  #44 opened 5 years ago by slerman12
  1

• Playing a different Sonic level?

  #45 opened 5 years ago by slerman12
  0

• "The frame skipping method is already implemented in the library."

  #47 opened 5 years ago by koryakinp
  0

• N-step returns

  #46 opened 5 years ago by slerman12
  0

• ViZDoomErrorException: Could not initialize SDL video

  #43 opened 5 years ago by Wentong-DST
  0

• can't open article link

  #41 opened 5 years ago by wlt992
  2

• Cannot get Q value prediction for next_state

  #39 opened 5 years ago by Christopheraburns
  0

• No usage of stacked_frames

  #37 opened 5 years ago by sven-hoek
  2

• Continuous output space scenario

  #34 opened 5 years ago by Thebaide
  2

• atari spaceinvaders tensorboard permission denied and models not found

  #35 opened 5 years ago by wishesrepo
  0

• Game not found

  #30 opened 5 years ago by Silence1995
  1