nottombrown rl-teacher issues

nottombrown / rl-teacher

Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback

MIT License

559 stars 95 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Problem solved

#45 jackyoung96 opened 1 year ago
0
Django and whitenoise versions

#44 bharatprakash opened 4 years ago
0
Django and whitenoise versions

#43 bharatprakash closed 4 years ago
0
Frozen screen issue

#42 sunit1409 opened 5 years ago
1
Back to pooled rollouts, but this time with random seed set using wor…

#41 ghost opened 6 years ago
0
Unique project for rl-teacher: help please

#40 JoelDeLeon opened 6 years ago
0
Changes to webapp to allow debugging of upload problems and providing feedback out of sequence

#39 mixuala closed 6 years ago
2
mujoco.py GLFW error: 65537, desc: b'The GLFW library is not initialized

#38 mixuala opened 6 years ago
0
WebApp blank, Incorrect ACL setting for Google Cloud Bucket

#37 mixuala closed 6 years ago
2
only pretraining comparisons appear in the labeling interface

#36 mixuala opened 7 years ago
2
Django error while trying to train an agent with human feedback

#35 Axxeption closed 7 years ago
3
Use Flask server insted of Google Cloud Storage (GCS)

#34 waxz closed 7 years ago
1
new commit run error

#33 zdx3578 closed 7 years ago
2
gsutil mb error

#32 zdx3578 closed 7 years ago
2
Support Mujoco version 1.5

#31 gautam1858 opened 7 years ago
6
No more Q states

#30 Raelifin closed 7 years ago
4
Broader Envs

#29 Raelifin closed 7 years ago
1
Back to pooled rollouts, but this time with random seed set using worker index.

#28 Raelifin closed 7 years ago
1
Allow running of unmodified envs with original `done` signals

#27 garymcintire closed 7 years ago
4
Video clips not showing when providing labels by human

#26 Guzzii closed 7 years ago
4
should we be constrained in using GCS

#25 tigerneil closed 7 years ago
2
Allow RoboSchool environments to remove Mujoco dependency

#24 nottombrown opened 7 years ago
3
Collect snapshots of agent parameters to allow sharing of trained agents

#23 nottombrown closed 7 years ago
0
Return a deepcopy of our split episodes

#22 nottombrown closed 7 years ago
0
Fix rollouts

#21 nottombrown closed 7 years ago
1
Debug PPO

#20 nottombrown closed 7 years ago
0
Remove unused logger.py file

#19 nottombrown closed 7 years ago
0
Move agents to directory

#18 nottombrown closed 7 years ago
0
Logging edge case errors

#17 Raelifin closed 7 years ago
0
Only generate 2 segments per label instead of 5

#16 Raelifin closed 7 years ago
1
Use multiple MPI workers with pposgd agent

#15 nottombrown closed 7 years ago
1
Fast random rollouts

#14 Raelifin closed 7 years ago
3
Properly log agent values from pposgd synth

#13 nottombrown closed 7 years ago
1
Configure system to use unmodified environments

#12 nottombrown opened 7 years ago
0
Add PPO

#11 nottombrown closed 7 years ago
0
Correct reward per episode values from PPOSGD

#10 nottombrown closed 7 years ago
1
Prevent video writing from stealing focus on OSX

#9 nottombrown opened 7 years ago
0
Remove Hungarian dimension notation

#8 nottombrown closed 7 years ago
0
Minor linting

#7 Raelifin closed 7 years ago
1
Refactor predictor

#6 nottombrown closed 7 years ago
0
Register environments as normal Gym envs

#5 nottombrown opened 7 years ago
0
Add PPO

#4 nottombrown closed 7 years ago
2
Add smoke tests

#3 nottombrown closed 7 years ago
0
Refactor comparison_collectors and label_schedules into modules

#2 nottombrown closed 7 years ago
0
Add short mode environments

#1 nottombrown closed 7 years ago
0