tensorflow/agents
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
PythonApache-2.0
Issues
- 0
Incompatibility between PPO collect policy and SquashToSpecNormal Distribution
#944 opened by CHEyy-85 - 2
ImportError: Attempted to load a reverb dynamic library, but it could not find the required symbols inside of TensorFlow.
#937 opened by ace510 - 2
- 0
Unexpected output from `actor_network`. Expected `Distribution` objects, but saw output spec: TensorSpec(shape=(4,), dtype=tf.int32, name=None)
#942 opened by mhdtslm - 0
- 0
to_n_step_transition returns wrong results if episode was truncated by the time limit wrapper and N > 1
#939 opened by zhezherun - 0
Updating outdated documentation
#938 opened by Nour-Aldein2 - 2
- 0
- 2
- 1
Error when running DynamicStepDriver with tf_agents
#936 opened by Jack-Rais - 1
Problem with AverageReturnMetric
#909 opened by billh0420 - 1
Type error in PolicySaver.save()
#929 opened by anmol438 - 0
Compatibility with gymnasium environments
#928 opened by anmol438 - 1
- 0
PolicySavedModelTrigger has no sweeping ability.
#927 opened by brianorbrain - 0
WARNING:tensorflow:Value in checkpoint could not be found in the restored object: (root).agent._optimizer._variables.1
#926 opened by huiyujie - 1
Errors when saving ranking policies
#891 opened by tottenjordan - 0
PPOAgent + MaskSplitterNetwork normalizes Mask when observation normalization is turned on.
#922 opened by BaLinuss - 0
got an unexpected keyword argument 'kwargs' when create_variables and unable to copy
#919 opened by hotamago - 0
Multi arm Multi play Setting
#917 opened by Akshaysharma29 - 1
Inference MAB
#914 opened by Akshaysharma29 - 1
[Fix this ASAP] TypeError : 'AtariEnv.render() takes 1 positional argument but 2 were given' and some environments can't be rendered
#911 opened by Skyisblue324 - 0
How to convert keras Model to DDQN QNetwork?
#910 opened by linfanzz - 0
- 2
DQN Tutorial.ipynb not working
#906 opened by tarobins - 0
- 1
- 0
How to run Code on Windows
#904 opened by MarleneBs - 1
Add support for gym_kwargs in suite_atari
#894 opened by msmith93 - 1
New to RL Agents, need help with policies
#892 opened by AhmadALBarqawi - 0
- 1
Q-Network wrong output spec
#896 opened by rissois - 2
- 1
- 0
Understanding parallel environments
#888 opened by b-fg - 0
- 0
Learning rate metric inconsistent depending on optimizer
#883 opened by b-fg - 0
- 1
Shape mismatch in DDPG agent's critic loss function? Shape mismatch between td_targets and q_values tensors
#854 opened by Pren7z - 0
ReverbAddTrajectoryObserver gives "The number of pending items is alarmingly high" error
#853 opened by adiaconu11 - 0
- 0
ModuleNotFoundError: No module named 'tf_agents.drivers'; 'tf_agents' is not a package
#849 opened by RayTsui - 0
Possible Bugs in CQL_SAC Example
#848 opened by ChengDaHaI - 1
Unable to load multiprocessing context for my validated custom gym environment.
#845 opened by Yash271100 - 2
- 0
Actor-PPOLearner with discrete Action on Windows
#841 opened by bennyfri - 0
- 0
- 0
ValueError when validating a gym environment with MultiDiscrete action space
#838 opened by heydarshahi