Author
Filter by author
Labels
Filter by label
Use alt + click/return to exclude labels.
Projects
Filter by project
Milestones
Filter by milestone
Reviews
Filter by reviews
Assignee
Filter by who’s assigned
Fix ActionRepeat to preserve the reward dtype and to not repeat actions on an implicit reset.
cla: yes
#204
opened Sep 7, 2019 by
alexlee-gk
Fixed: add_batch method observer on PyUniformReplayBuffer bug #198
cla: yes
#200
opened Aug 29, 2019 by
j0rd1smit
Fixed: ActorDistributionNetwork crashes when action_spec is not a tensor_spec
cla: yes
#199
opened Aug 29, 2019 by
j0rd1smit
Wrap envs with multidiscrete action space into discrete action space
cla: yes
#143
opened Jun 18, 2019 by
seungjaeryanlee
If the current time step is the last, step() should call reset() automatically
cla: yes
#116
opened May 23, 2019 by
ageron
Added an option for PPO to train on incomplete episodes.
cla: yes
#36
opened Mar 15, 2019 by
PeterZhizhin
ProTip!
Exclude everything labeled
bug with -label:bug.