Skip to content

/ stable-baselines

forked from openai/baselines

Pinned issues

Tensorflow 2.0 support?
#366 by heron1 was closed Mar 8, 2020
Closed 20
V3.0 implementation design
#576 by araffin was closed May 26, 2020
Closed 44
V3 new backend: PyTorch? and the future of Stable Baselines
#733 opened Mar 8, 2020 by araffin
Open 9
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

104 Open 665 Closed
104 Open 665 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels.
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
Retrain from updated environment No tech support more information needed question
#1003 opened Sep 12, 2020 by anguyenbus
4
How to design an actor-critic network with two non-shared LSTMs that take separate inputs? question
#1002 opened Sep 12, 2020 by baiydaavi
1
Zero_grad() question
#997 opened Sep 9, 2020 by amirhosseinzlf
1
[question] Combined continuous and discrete action space custom gym env question
#995 opened Sep 4, 2020 by kosmylo
1
testing model the second time gives UnpicklingError: A load persistent id instruction was encountered, but no persistent_load function was specified. more information needed
#994 opened Sep 1, 2020 by jandevries1421353151
4
TypeError: object of type 'int' has no len() bug custom gym env
#977 opened Aug 13, 2020 by KeeratKG
2
[Question] How to save and load a trained model into Tensorflow 1 and 2? question
#974 opened Aug 12, 2020 by VSZM
5
[question] RL algorithms for continuous action spaces (DDPG and TD3) unable to eliminate steady-state error in custom environment. custom gym env question
#963 opened Aug 3, 2020 by wilsonsamarques
2
[Question] Using PPO1 on a cluster question
#957 opened Jul 20, 2020 by AlessandroZavoli
2
[Question] Profiling with custum environment and MPI custom gym env question
#953 opened Jul 18, 2020 by AlessandroZavoli
1
Retraining model after loading not working while following #30 custom gym env more information needed question
#950 opened Jul 17, 2020 by aadnesd
5
Network architecture keyword argument consistency enhancement
#948 opened Jul 16, 2020 by cisprague
1
Maybe there is one problem in implementing the class PrioritizedReplayBuffer bug
#941 opened Jul 13, 2020 by UPUPGOO
9
Loading in a model with Prioritized Experience Replay causes uninitialized model? more information needed
#940 opened Jul 13, 2020 by jandevries123
17
Pre-Training Problem more information needed windows
#932 opened Jul 8, 2020 by FabioPINO
9
Trained policy export to ONNX via PyTorch question
#922 opened Jul 5, 2020 by crobarcro
2
[question] PPO2 pretrain always resets weights? bug question
#921 opened Jul 2, 2020 by SolaWeng
5
[question] Specify a prior over action distribution? question
#903 opened Jun 23, 2020 by juliuskittler
4
[question] SAC target q nets may be updated many times in each round? bug
#900 opened Jun 21, 2020 by xuanqing94 v2.10.1
5
Value Function Normalization enhancement v3
#892 opened Jun 16, 2020 by huvar
1
Read errors when running PPO1 with MPI question
#886 opened Jun 8, 2020 by tirafesi
3
error while using LstmPolicy question windows
#882 opened Jun 4, 2020 by pirate-lofy
3
[feature request] Add maximum time steps parameter to evaluation function to protect against infinite episodes enhancement
#876 opened Jun 3, 2020 by philwinder
1
[feature request] Plotting additional info collected by monitor using results_plotter enhancement
#872 opened May 28, 2020 by nisheeth-golakiya
4
Should `TensorboardWriter` close its `tf.summary.FileWriter`? bug help wanted
#855 opened May 14, 2020 by shwang
4
ProTip! no:milestone will show everything without a milestone.
You can’t perform that action at this time.