forked from openai/baselines
-
Notifications
You must be signed in to change notification settings - Fork 724
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
True rewards remaining "zero" in the trajectories in stable baselines2 for custom environments
custom gym env
Issue related to Custom Gym Env
question
Further information is requested
#1167
opened Jul 26, 2022 by
moizuet
Deep Q-value network evaluation in SAC algorithm
question
Further information is requested
#1166
opened Jul 19, 2022 by
moizuet
1D Vector of floats as an observation space
question
Further information is requested
#1164
opened Jun 8, 2022 by
WilliamFlinchbaugh
Problem retraining PPO1 model and using Tensorflow with Stable Baselines 2
question
Further information is requested
#1154
opened Mar 12, 2022 by
durantagre
Running Stable Baselines on M1 Macs?
question
Further information is requested
#1152
opened Feb 25, 2022 by
adamnhaka
[question] How do I load a tensorflow ckpt?
more information needed
Please fill the issue template completely
question
Further information is requested
RTFM
Answer is the documentation
#1147
opened Jan 2, 2022 by
Syzygianinfern0
evaluate_policy() crashes with PPO2 policies trained on vectorized environments [bug]
duplicate
This issue or pull request already exists
question
Further information is requested
#1141
opened Oct 3, 2021 by
balisujohn
PPO2 implementation details?
question
Further information is requested
#1140
opened Sep 29, 2021 by
FabioPINO
[question] What is the proper way to log metrics at the end of each epoch when epochs are variable in length?
custom gym env
Issue related to Custom Gym Env
question
Further information is requested
#1139
opened Sep 23, 2021 by
DavidBellamy
Resume Training with Previous Experience (state-action-state')?
question
Further information is requested
#1134
opened Aug 26, 2021 by
wenjunli-0
Tensorboard HPARAMS with DDQN #question
question
Further information is requested
#1128
opened Jul 7, 2021 by
Arione94
VecNormalize for multiple training environments?
question
Further information is requested
#1114
opened May 10, 2021 by
jdshaolinstar
[question] Suggested Hyperparams for A2C with highway-env
custom gym env
Issue related to Custom Gym Env
question
Further information is requested
#1100
opened Mar 15, 2021 by
pierrekhouryy
GAIL throws error when obs space is MultiDiscrete
documentation
Documentation should be updated
#1096
opened Mar 3, 2021 by
SurferZergy
[feature request] LstmPolicy does not support using net_arch with feature_extraction="cnn"
enhancement
New feature or request
#1071
opened Jan 18, 2021 by
GiliR4t1qbit
[question] EvalCallback using MPI
question
Further information is requested
#1069
opened Jan 15, 2021 by
davidADSP
Does stable baselines provide an automatic way of computing the sample efficiency of an RL algorithm?
question
Further information is requested
#1052
opened Dec 1, 2020 by
nbro
Episode rewards not updated before being used by callback.on_step()
good first issue
Good for newcomers
question
Further information is requested
#1046
opened Nov 23, 2020 by
calerc
[question] Issue with multiple instances for DDPG-MPI from stable-baselines[mpi]
question
Further information is requested
#1044
opened Nov 21, 2020 by
UtkarshMishra04
What would be the easiest way to initialise the value or policy networks differently?
question
Further information is requested
#1039
opened Nov 14, 2020 by
nbro
Possible to run a full episode and collate results? For training on real-time hardware.
custom gym env
Issue related to Custom Gym Env
question
Further information is requested
#1036
opened Nov 10, 2020 by
crobarcro
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.