-
Notifications
You must be signed in to change notification settings - Fork 720
Pull requests: tensorflow/agents
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Typo fix on 5_replay_buffers_tutorial.ipynb
cla: yes
#304
by pbmartins
was merged Feb 7, 2020
Loading…
Fix minor typo in 10_checkpointer_policysaver tutorial
cla: yes
#370
by ahafftka
was merged May 18, 2020
Loading…
Use a separate counter variable for train_step_counter in PPOAgent
cla: yes
#358
by leroidauphin
was closed May 1, 2020
Loading…
Support scalar action spaces in the actor distribution network.
cla: no
#343
by leroidauphin
was closed May 20, 2020
Loading…
Remove uses of
tf.compat.v1.scatter_update
cla: yes
#333
by leroidauphin
was closed Mar 1, 2021
Loading…
Update common.replicate to support replicating scalar tensors
cla: yes
#328
by leroidauphin
was merged Mar 19, 2020
Loading…
Set TFPyEnv's reward shape per wrapped env's time_step_spec.
cla: yes
#325
by mhe500
was merged Mar 19, 2020
Loading…
Make the NumEpisodesObserver count all episodes in a batch of trajectories
cla: yes
#311
by leroidauphin
was merged Feb 27, 2020
Loading…
Peter zhizhin: Added an option for PPO to train on incomplete episode
cla: yes
#306
by tfboyd
was merged Feb 18, 2020
Loading…
Eps Greedy Policy fix for policy info containing tensors of rank > 1.
cla: yes
#252
by mhe500
was merged Dec 6, 2019
Loading…
Remove ValueError of q_value dimension in ddpg_agent critic_loss
cla: yes
#278
by cjy1992
was closed Aug 21, 2020
Loading…
added editorconfig to help to follow the tensorflow style
cla: yes
#272
by pana1990
was closed Feb 6, 2020
Loading…
Support for 'training' flag (for dropout) in DQN Agent.
cla: yes
#269
by mhe500
was closed Dec 22, 2019
Loading…
ProTip!
no:milestone will show everything without a milestone.