forked from openai/baselines
-
Notifications
You must be signed in to change notification settings - Fork 727
Issues: hill-a/stable-baselines
V3 new backend: PyTorch? and the future of Stable Baselines
#733
by araffin
was closed Mar 2, 2021
Closed
10
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Possible problems in total_episode_reward_logger
enhancement
New feature or request
#236
opened Mar 15, 2019 by
rasoolfa
Beta distribution as policy for environments with bounded continuous action spaces [feature request]
enhancement
New feature or request
experimental
Experimental Feature
help wanted
Help from contributors is needed
#112
opened Dec 4, 2018 by
skervim
LSTM policies are broken for PPO1 and TRPO
bug
Something isn't working
help wanted
Help from contributors is needed
#140
opened Dec 20, 2018 by
ernestum
[bug] PPO2 episode reward summaries are written incorrectly for VecEnvs
bug
Something isn't working
#143
opened Dec 22, 2018 by
shwang
Allow nd arrays for MultiDiscrete
enhancement
New feature or request
#151
opened Jan 8, 2019 by
kosii
Training LSTMs involves lots of data transformation
enhancement
New feature or request
help wanted
Help from contributors is needed
#158
opened Jan 11, 2019 by
ernestum
Training with recurrent cells from keras
documentation
Documentation should be updated
enhancement
New feature or request
#161
opened Jan 13, 2019 by
ernestum
[question] Reproduce the result of PPO on RoboschoolHumanoidFlagrunHarder
question
Further information is requested
#179
opened Jan 30, 2019 by
doviettung96
[Question] How best to implement self-play/multiple agents in the same environment?
question
Further information is requested
#181
opened Jan 31, 2019 by
brokenloop
ACKTR hangs/crashes
help wanted
Help from contributors is needed
#196
opened Feb 11, 2019 by
EliasHasle
Trying to understand hardware limitations for parallelizing PPO2 [question]
question
Further information is requested
#201
opened Feb 14, 2019 by
SerialIterator
[question] Using keras in Custom Policy
question
Further information is requested
#220
opened Mar 4, 2019 by
batu
Guide for using LSTM with PPO2
question
Further information is requested
#231
opened Mar 11, 2019 by
pulver22
Trying to understand how the LSTM policy works
documentation
Documentation should be updated
question
Further information is requested
#278
opened Apr 17, 2019 by
Caisho
Graph is always saved, resulting in large log files
enhancement
New feature or request
#300
opened May 1, 2019 by
dniku
[Feature Proposal] Intrinsic Reward VecEnvWrapper
enhancement
New feature or request
experimental
Experimental Feature
v3
Discussion about V3
#309
opened May 6, 2019 by
araffin
DQN implementation that supports continuous action spaces (NAF)
enhancement
New feature or request
experimental
Experimental Feature
question
Further information is requested
#311
opened May 6, 2019 by
padalous
Recording Expert Data from myself in Discrete Action Space
question
Further information is requested
#319
opened May 10, 2019 by
JankyOo
[question] Why are RL CNNs so shallow?
question
Further information is requested
#367
opened Jun 11, 2019 by
AlanKuurstra
[Feature Proposal] Add NaN and Inf checking to RL models
enhancement
New feature or request
#368
opened Jun 11, 2019 by
hill-a
[Feature Request] Interaction Drivers/Runners
enhancement
New feature or request
#381
opened Jun 21, 2019 by
jmribeiro
ACKTR model crashes using CnnLnLstmPolicy
custom gym env
Issue related to Custom Gym Env
#387
opened Jun 25, 2019 by
MartinBertran
[Feature Request] Multiple environments per process
enhancement
New feature or request
#390
opened Jun 27, 2019 by
neighthan
Previous Next
ProTip!
Exclude everything labeled
bug
with -label:bug.