Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / keras-rl/keras-rl issues and pull requests
#399 - AttributeError: Tensor.op is meaningless when eager execution is enabled.
Issue -
State: open - Opened by 2462370039 4 months ago
- 1 comment
#398 - info action masks fails
Issue -
State: open - Opened by DavidReds 5 months ago
#397 - Recommendation to synchronize tf, keras and keras rl versions?
Issue -
State: open - Opened by satyrmipt 8 months ago
- 3 comments
#396 - ValueError: Could not interpret optimizer identifier: <keras.src.optimizers.adam.Adam object at 0x79d9071160e0>
Issue -
State: open - Opened by YikunHan42 9 months ago
#395 - Frame Skipping in DQN
Issue -
State: open - Opened by sandra-sys 12 months ago
#394 - Update for tensorflow>=2.11 & gym>=0.26
Pull Request -
State: open - Opened by yuriiz about 1 year ago
- 1 comment
#393 - Keras-RL2 DQN agent fails to learn on some environments
Issue -
State: open - Opened by rajfly over 1 year ago
#392 - gym.Env.reset() no longer returns observation of type np.array but a tuple of (observation, info)
Issue -
State: open - Opened by AldairCB over 1 year ago
#391 - Add CI
Pull Request -
State: closed - Opened by testytestytestytest almost 2 years ago
#390 - Add metrics in episode_logs
Pull Request -
State: open - Opened by lbosk over 2 years ago
#389 - Define get_weights and set_weights
Pull Request -
State: open - Opened by lbosk over 2 years ago
#388 - Value error when running DQN.fit
Issue -
State: open - Opened by GravermanDev over 2 years ago
- 2 comments
#387 - Multiple Actions in DQN (binary action vector)
Issue -
State: open - Opened by 2019hc04089 over 2 years ago
#386 - How to set the "nb_steps_warmup" and "nb_steps" properly?
Issue -
State: open - Opened by Beliefuture over 2 years ago
- 1 comment
#385 - Examples update
Pull Request -
State: open - Opened by javadi almost 3 years ago
- 1 comment
#384 - <rl.agents.dqn.DQNAgent object at 0x000001FE98873A88>
Issue -
State: closed - Opened by Saber-xxf almost 3 years ago
- 1 comment
Labels: wontfix
#383 - which version the tensorflow and numpy it is inDQN_carpole?
Issue -
State: closed - Opened by Saber-xxf almost 3 years ago
- 1 comment
Labels: wontfix
#382 - how to implement a custom environment?
Issue -
State: closed - Opened by harleyxu-xhl about 3 years ago
- 1 comment
Labels: wontfix
#381 - ImportError: cannot import name 'PrioritizedMemory' from 'rl.memory'
Issue -
State: closed - Opened by avani17101 about 3 years ago
- 1 comment
Labels: wontfix
#380 - Issue importing keras-rl on tensorflow-macos
Issue -
State: open - Opened by Sebewe about 3 years ago
- 4 comments
#379 - Training performance is quite slow
Issue -
State: closed - Opened by Cpt-Falcon over 3 years ago
- 3 comments
Labels: wontfix
#378 - Undocumented version requirements for python, tensorflow, and keras
Issue -
State: closed - Opened by jakurucar over 3 years ago
- 3 comments
Labels: wontfix
#377 - Module 'keras.utils.generic_utils' has no attribute 'populate_dict_with_module_objects'
Issue -
State: closed - Opened by rhalaly over 3 years ago
- 2 comments
#376 - ValueError: probabilities contain NaN in policy.py
Issue -
State: closed - Opened by ghost over 3 years ago
- 5 comments
Labels: wontfix
#375 - [Question] Custom Environment
Issue -
State: closed - Opened by abeerM over 3 years ago
- 1 comment
Labels: wontfix
#374 - 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)
Issue -
State: closed - Opened by shravansuthar210 almost 4 years ago
- 4 comments
Labels: wontfix
#373 - Numpy data wrangling in rl/callbacks.py
Issue -
State: closed - Opened by jan-polivka almost 4 years ago
- 1 comment
Labels: wontfix
#372 - DDPG worked well but not CDQN or NAF !
Issue -
State: closed - Opened by B-Yassine almost 4 years ago
- 1 comment
#371 - Please help me, I have a problem with DQNAgent.
Issue -
State: closed - Opened by hemsatrakol almost 4 years ago
- 12 comments
Labels: wontfix
#370 - Spelling Error update
Pull Request -
State: closed - Opened by DemitriM almost 4 years ago
#369 - 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)?
Issue -
State: closed - Opened by malsaidi93 about 4 years ago
- 1 comment
Labels: wontfix
#368 - Added external project to Readme
Pull Request -
State: closed - Opened by stefanbschneider about 4 years ago
#367 - Dimension does not match for tuple space
Issue -
State: closed - Opened by jxiw about 4 years ago
- 1 comment
Labels: wontfix
#366 - Examples don't work anymore
Issue -
State: closed - Opened by iirekm about 4 years ago
- 6 comments
Labels: wontfix
#365 - Stores reward_mean, reward_std in the FileLogger
Pull Request -
State: open - Opened by jayaneetha about 4 years ago
#364 - raise ValueError 'Critic "{}" does not have enough inputs when run ddpg_pendulum.py
Issue -
State: closed - Opened by HankerSia over 4 years ago
- 1 comment
Labels: wontfix
#363 - DQL
Issue -
State: closed - Opened by johan606303 over 4 years ago
- 2 comments
Labels: wontfix
#362 - Cannot import CallbackList
Issue -
State: closed - Opened by FitMachineLearning over 4 years ago
- 7 comments
Labels: wontfix
#361 - Replace image_dim_ordering in Atari DQN example
Pull Request -
State: open - Opened by danielduffield over 4 years ago
#360 - Fix minor spelling errors in the core file.
Pull Request -
State: open - Opened by danielduffield over 4 years ago
#359 - AssertionError: assert q_values.shape == (self.nb_actions,)
Issue -
State: closed - Opened by vachanda over 4 years ago
- 1 comment
Labels: wontfix
#358 - Fix for Issue #348: len is not well defined for symbolic Tensors
Pull Request -
State: open - Opened by msat59 over 4 years ago
- 3 comments
#357 - Update readme with recommended tf version.
Pull Request -
State: closed - Opened by dmckinno over 4 years ago
- 1 comment
#356 - Keras RL for another externel Enviroment
Issue -
State: closed - Opened by Jekso over 4 years ago
- 4 comments
#355 - Using Keras RL in production
Issue -
State: closed - Opened by zolekode over 4 years ago
- 1 comment
Labels: wontfix
#354 - Is this project dead?
Issue -
State: closed - Opened by khayamgondal over 4 years ago
- 3 comments
Labels: wontfix
#353 - Hotfix/not well defined shape
Pull Request -
State: open - Opened by LyWangPX almost 5 years ago
- 1 comment
#352 - When the A3C and PPO can be implemented?
Issue -
State: closed - Opened by GIS-PuppetMaster almost 5 years ago
- 1 comment
Labels: wontfix
#351 - Issue #348: len is not well defined for symbolic Tensors
Pull Request -
State: open - Opened by rckitson almost 5 years ago
- 2 comments
#350 - EXAMPLE : Loading Models After fully trained
Issue -
State: closed - Opened by STRATZ-Ken almost 5 years ago
- 7 comments
Labels: wontfix
#349 - 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.
Issue -
State: closed - Opened by toksis almost 5 years ago
#348 - len is not well defined for symbolic tensors *AND* using a `tf.Tensor` as a Python `bool` is not allowed in Graph execution
Issue -
State: closed - Opened by EduardDurech almost 5 years ago
- 16 comments
Labels: wontfix
#347 - I would like to use as env my Flow-Project script
Issue -
State: closed - Opened by gioiav almost 5 years ago
- 1 comment
Labels: wontfix
#346 - Remove manual backend selection of Keras for K.switch
Pull Request -
State: open - Opened by shijianjian about 5 years ago
#345 - AttributeError: 'Adam' object has no attribute '_name'
Issue -
State: closed - Opened by palbha about 5 years ago
- 4 comments
Labels: wontfix
#344 - Can anyone suggest what version of tensorflow is being used in background
Issue -
State: closed - Opened by palbha about 5 years ago
- 10 comments
#343 - Where is the environment specified in DQNAgent
Issue -
State: closed - Opened by kdawar1 about 5 years ago
- 1 comment
Labels: wontfix
#342 - Asking for some clarification in docs about agent's methods
Issue -
State: closed - Opened by KIC about 5 years ago
- 1 comment
Labels: wontfix
#341 - Instrument Weights & Biases
Pull Request -
State: closed - Opened by Xyzrr about 5 years ago
- 1 comment
#340 - Monitor wrapper. Tried to reset environment which is not done
Issue -
State: closed - Opened by dizcza about 5 years ago
- 1 comment
Labels: wontfix
#339 - image_dim_ordering, used in example dqn agent, removed in Keras 2.2.5
Issue -
State: closed - Opened by travisp about 5 years ago
- 1 comment
#338 - TypeError with WhiteningNormalizerProcessor
Issue -
State: closed - Opened by stefanbschneider about 5 years ago
- 1 comment
Labels: wontfix
#337 - will the dqn.fit reset the model weight?
Issue -
State: closed - Opened by yhzhang1 about 5 years ago
- 2 comments
Labels: wontfix
#336 - /keras-rl/examples/dqn_atari.py" AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'
Issue -
State: closed - Opened by loveyandex about 5 years ago
- 1 comment
Labels: wontfix
#335 - /keras-rl/examples/dqn_atari.py" AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'
Issue -
State: closed - Opened by loveyandex about 5 years ago
- 1 comment
Labels: wontfix
#334 - Using Keras-RL for anything other than the examples
Issue -
State: closed - Opened by gregarious9612 about 5 years ago
- 2 comments
Labels: wontfix
#333 - how to distinguish that a decision is greedy or not
Issue -
State: closed - Opened by vxgu86 about 5 years ago
- 1 comment
Labels: wontfix
#332 - docs are sad
Issue -
State: closed - Opened by bionicles about 5 years ago
- 1 comment
Labels: wontfix
#331 - Update DQN readme, DDPG code to include TD3 variant
Pull Request -
State: open - Opened by yujia21 about 5 years ago
#330 - Fix CEM agent (prefer 'good' weights instead of 'lucky' weights)
Pull Request -
State: open - Opened by Nikolay-Lysenko about 5 years ago
#329 - AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'
Issue -
State: closed - Opened by stephenscki about 5 years ago
- 2 comments
Labels: wontfix
#328 - online testing after training on batch dataset
Issue -
State: closed - Opened by mg64ve over 5 years ago
- 2 comments
Labels: wontfix
#327 - tanh activation result less than -1
Issue -
State: closed - Opened by salos1982 over 5 years ago
- 3 comments
Labels: wontfix
#326 - history not have mean_q
Issue -
State: closed - Opened by hardy110 over 5 years ago
- 1 comment
Labels: wontfix
#325 - Determine the Probabilities from a prediction.
Issue -
State: closed - Opened by STRATZ-Ken over 5 years ago
- 1 comment
#324 - Please reopen #161
Issue -
State: closed - Opened by CameronBeebe over 5 years ago
- 1 comment
Labels: wontfix
#323 - What happened to PrioritizedMemory ? I got an import error while using this memory function, when i checked the rl/memory.py there is no mention of PrioritizedMemory, why is that?
Issue -
State: closed - Opened by tarscase over 5 years ago
- 2 comments
Labels: wontfix
#322 - NotImplementedError
Issue -
State: closed - Opened by shmpwk over 5 years ago
- 1 comment
Labels: wontfix
#320 - Environments with no terminal state
Issue -
State: closed - Opened by tahaeghtesad over 5 years ago
- 2 comments
Labels: wontfix
#318 - Add Tensorflow 2 Keras Support
Issue -
State: closed - Opened by tensorneko over 5 years ago
- 4 comments
Labels: wontfix
#317 - DDPG Agent batch shape problem
Issue -
State: closed - Opened by wmeints over 5 years ago
- 2 comments
Labels: wontfix
#314 - Actions values out of box limits.
Issue -
State: closed - Opened by mquinteiro over 5 years ago
- 6 comments
Labels: wontfix
#313 - NAFAgent bug?
Issue -
State: closed - Opened by Amndeep7 over 5 years ago
- 8 comments
Labels: wontfix
#312 - Dueling DQN architecture doesn't split dense layer into streams
Issue -
State: closed - Opened by Qinusty over 5 years ago
- 8 comments
Labels: wontfix
#311 - add cn README
Pull Request -
State: open - Opened by kaixinbaba over 5 years ago
- 1 comment
#310 - All the examples deal with the problems using the discrete action space. I am wondering if I can use the multi_discrete action space. Can the DQNAgent still work?
Issue -
State: closed - Opened by tinyxuyan over 5 years ago
- 2 comments
Labels: wontfix
#306 - Keras-RL adding extra dimension to my input
Issue -
State: closed - Opened by ndeshp2s over 5 years ago
- 7 comments
Labels: wontfix
#303 - Plans to continue development?
Issue -
State: closed - Opened by jarlva over 5 years ago
- 5 comments
Labels: wontfix
#302 - Replace mutable default arguments with None
Pull Request -
State: open - Opened by Qinusty over 5 years ago
- 1 comment
#294 - Custom keras.callbacks.History() option as fit method argument
Pull Request -
State: open - Opened by VinQbator almost 6 years ago
- 1 comment
#288 - Saving/Loading/resuming agent state and weights
Issue -
State: closed - Opened by jarlva almost 6 years ago
- 2 comments
#285 - DDPG on Discrete Action Space
Issue -
State: open - Opened by Psyf almost 6 years ago
- 3 comments
#278 - Policy gradient agent - no intention to add?
Issue -
State: open - Opened by jonilaserson almost 6 years ago
- 7 comments
Labels: contribution-welcome
#268 - Pendulum examples don't work
Issue -
State: closed - Opened by mdavis-xyz about 6 years ago
- 8 comments
Labels: bug, contribution-welcome
#255 - DQNAgent has no attribute optimizer
Issue -
State: closed - Opened by nisbus about 6 years ago
- 4 comments
Labels: wontfix
#248 - AssertionError: q_values.shape == (self.batch_size, self.nb_actions)
Issue -
State: closed - Opened by niclaswue about 6 years ago
- 4 comments
Labels: wontfix
#211 - What if not all actions are valid
Issue -
State: closed - Opened by imandr over 6 years ago
- 11 comments
Labels: wontfix
#160 - input shape in DDPG
Issue -
State: closed - Opened by ffrige almost 7 years ago
- 4 comments
Labels: wontfix
#141 - TensorBoard callback doesn't work
Issue -
State: closed - Opened by ruippeixotog about 7 years ago
- 4 comments
#109 - What are train_interval, nb_steps_warmup_critic and nb_steps_warmup_actor?
Issue -
State: closed - Opened by ViktorM over 7 years ago
- 3 comments
Labels: wontfix