keras-rl/keras-rl

Issues

• Recommendation to synchronize tf, keras and keras rl versions?

  #397 opened 2 months ago by satyrmipt
  3

• Issue importing keras-rl on tensorflow-macos

  #380 opened 3 years ago by Sebewe
  4

• ValueError: Could not interpret optimizer identifier: <keras.src.optimizers.adam.Adam object at 0x79d9071160e0>

  #396 opened 3 months ago by YikunHan42
  0

• Frame Skipping in DQN

  #395 opened 6 months ago by sandra-sys
  0

• Keras-RL2 DQN agent fails to learn on some environments

  #393 opened a year ago by rajfly
  0

• ValueError: probabilities contain NaN in policy.py

  #376 opened 2 years ago
  5

• gym.Env.reset() no longer returns observation of type np.array but a tuple of (observation, info)

  #392 opened a year ago by AldairCB
  0

• Cannot import CallbackList

  #362 opened 3 years ago by FitMachineLearning
  7

• Please help me, I have a problem with DQNAgent.

  #371 opened 3 years ago by hemsatrakol
  12

• Value error when running DQN.fit

  #388 opened 2 years ago by GravermanDev
  2

• len is not well defined for symbolic tensors *AND* using a `tf.Tensor` as a Python `bool` is not allowed in Graph execution

  #348 opened 3 years ago by EduardDurech
  16

• <rl.agents.dqn.DQNAgent object at 0x000001FE98873A88>

  #384 opened 2 years ago by Saber-xxf
  1

• which version the tensorflow and numpy it is inDQN_carpole?

  #383 opened 2 years ago by Saber-xxf
  1

• Undocumented version requirements for python, tensorflow, and keras

  #378 opened 2 years ago by jakurucar
  3

• how to implement a custom environment?

  #382 opened 2 years ago by harleyxu-xhl
  1

• ImportError: cannot import name 'PrioritizedMemory' from 'rl.memory'

  #381 opened 2 years ago by avani17101
  1

• [Question] Custom Environment

  #375 opened 2 years ago by abeerM
  1

• Training performance is quite slow

  #379 opened 2 years ago by Cpt-Falcon
  3

• Multiple Actions in DQN (binary action vector)

  #387 opened 2 years ago by 2019hc04089
  0

• How to set the "nb_steps_warmup" and "nb_steps" properly?

  #386 opened 2 years ago by Beliefuture
  1

• C:\Python\Python37\lib\site-packages\keras_rl-0.4.2-py3.7.egg\rl\agents\dqn.py in __init__(self, model, policy, test_policy, enable_double_dqn, enable_dueling_network, dueling_type, *args, **kwargs)

  #374 opened 3 years ago by shravansuthar210
  4

• Module 'keras.utils.generic_utils' has no attribute 'populate_dict_with_module_objects'

  #377 opened 3 years ago by rhalaly
  2

• Numpy data wrangling in rl/callbacks.py

  #373 opened 3 years ago by jan-gebauer
  1

• Examples don't work anymore

  #366 opened 3 years ago by iirekm
  6

• I am trying to visualize the results of an example I ran (sarsa.cartpole). The example ran fine and I got the results of the training, however, I can't visualize the results. Following the instructions given (from rl.callbacks import WandbLogger) raises an error [cannot import name 'WandbLogger']. The package (wandb) is installed and all the dependecies are installed. If this does not work, how else can I visualize the results and store the generated data (episode, reward, action,...etc)?

  #369 opened 3 years ago by malsaidi93
  1

• raise ValueError 'Critic "{}" does not have enough inputs when run ddpg_pendulum.py

  #364 opened 3 years ago by HankerSia
  1

• Dimension does not match for tuple space

  #367 opened 3 years ago by jxiw
  1

• DDPG worked well but not CDQN or NAF !

  #372 opened 3 years ago by B-Yassine
  1

• DQL

  #363 opened 4 years ago by johan606303
  2

• Can anyone suggest what version of tensorflow is being used in background

  #344 opened 4 years ago by palbha
  10

• Is this project dead?

  #354 opened 4 years ago by khayamgondal
  3

• AssertionError: assert q_values.shape == (self.nb_actions,)

  #359 opened 4 years ago by vachanda
  1

• Using Keras RL in production

  #355 opened 4 years ago by zolekode
  1

• EXAMPLE : Loading Models After fully trained

  #350 opened 4 years ago by STRATZ-Ken
  7

• When the A3C and PPO can be implemented?

  #352 opened 4 years ago by GIS-PuppetMaster
  1

• Keras RL for another externel Enviroment

  #356 opened 4 years ago by Jekso
  4

• I would like to use as env my Flow-Project script

  #347 opened 4 years ago by gioiav
  1

• AttributeError: 'Adam' object has no attribute '_name'

  #345 opened 4 years ago by palbha
  3

• will the dqn.fit reset the model weight?

  #337 opened 4 years ago by yhzhang1
  2

• Where is the environment specified in DQNAgent

  #343 opened 4 years ago by kdawar1
  1

• Asking for some clarification in docs about agent's methods

  #342 opened 4 years ago by KIC
  1

• Processor's def process_reward(self, reward), def process_step(self, observation, reward, done, info): wont return the value of reward for atari and retro.

  #349 opened 4 years ago by toksis
  0

• Monitor wrapper. Tried to reset environment which is not done

  #340 opened 4 years ago by dizcza
  1

• TypeError with WhiteningNormalizerProcessor

  #338 opened 4 years ago by stefanbschneider
  1

• Using Keras-RL for anything other than the examples

  #334 opened 4 years ago by gregarious9612
  2

• /keras-rl/examples/dqn_atari.py" AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'

  #336 opened 4 years ago by loveyandex
  1

• /keras-rl/examples/dqn_atari.py" AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'

  #335 opened 4 years ago by loveyandex
  1

• how to distinguish that a decision is greedy or not

  #333 opened 4 years ago by vxgu86
  1

• docs are sad

  #332 opened 4 years ago by bionicles
  1

• image_dim_ordering, used in example dqn agent, removed in Keras 2.2.5

  #339 opened 5 years ago by travisp
  1