issues
search
araffin
/
sbx
SBX: Stable Baselines Jax (SB3 + Jax)
MIT License
328
stars
32
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Optimize the log of the entropy coeff instead of the entropy coeff
#56
jamesheald
opened
19 hours ago
6
SB3 and SBX versions of SAC have radically different behaviours
#55
jamesheald
opened
1 day ago
6
[Question] fps drops significantly over time
#54
oxkitsune
opened
1 week ago
0
[Question] framestack and train_freq for sbx
#53
Jackflyingzzz
opened
2 weeks ago
2
Feat/rainbow
#50
araffin
opened
2 months ago
0
Add CNN support for DQN
#49
araffin
closed
2 months ago
1
[Feature Request] Dict Obs Spaces Support
#48
alexpalms
opened
4 months ago
2
Fix warning and remove DroQ class in favor of SAC config
#47
araffin
closed
4 months ago
0
Hotfix - Return the new updated key in function _train
#46
theovincent
closed
5 months ago
2
self.key is never updated
#45
theovincent
closed
5 months ago
2
[Bug] TQC Hyperparameter optimization: Results do not match the reference. This is likely a bug/unexpected loss of precision.
#44
edmund735
closed
2 months ago
2
Support for setting the target entropy
#43
jan1854
closed
6 months ago
0
[Bug] TQC Entropy Coefficient
#42
edmund735
closed
6 months ago
2
Allow to pass custom activation function in `policy_kwargs`
#41
paolodelia99
closed
6 months ago
1
[Feature Request] Recurrent policies
#40
jamesheald
opened
6 months ago
13
Fix for new tensorflow probability version
#39
araffin
closed
6 months ago
0
set tensorflow-probability version in setup.py
#38
tonyspumoni
closed
6 months ago
1
[Feature Request] Passing custom activation functon in policy_kwargs
#37
paolodelia99
closed
6 months ago
2
Implemented CrossQ
#36
danielpalen
closed
6 months ago
10
[Question] Why is fps much lower than CPU if using GPU
#35
fanliaoooo
closed
6 months ago
1
[Question] MaskablePPO support
#34
GuillermoHijano
closed
6 months ago
1
[Question] TypeError when exporting a model to PyTorch in SBX
#33
LennertEvens
closed
6 months ago
3
[Question] `MultiInputPolicy` not supported (DroQ)
#32
jbirnick
opened
7 months ago
1
[Question] Speedup compared to SB3
#31
thomashirtz
closed
6 months ago
1
Support for MultiDiscrete and MultiBinary action spaces in PPO
#30
jan1854
closed
7 months ago
3
[Bug] AttributeError: module 'tensorflow.python.util.tf_inspect' has no attribute 'Parameter'
#29
ashok-arora
closed
6 months ago
9
Add CrossQ
#28
araffin
closed
6 months ago
6
SBX becomes super slow when number of cpus are limited
#27
Deepakgthomas
closed
8 months ago
2
[Feature Request] Support Optax Optimizer Schedules
#25
bradleypick
closed
8 months ago
4
Fix train signature and update type hints
#24
araffin
closed
8 months ago
0
Mujoco XLA - MJX Integration
#23
matinmoezzi
closed
6 months ago
1
[Feature Request] Update type annotations
#22
araffin
closed
8 months ago
0
Added support for large values for gradient_steps to SAC, TD3, and TQC
#21
jan1854
closed
8 months ago
12
Fix replay buffer device at load time
#20
araffin
closed
9 months ago
0
[Feature Request] Multi-Discrete action spaces for PPO
#19
tobiasmerkt
closed
7 months ago
3
Add flatten layer and update dependencies
#18
araffin
closed
11 months ago
0
Custom env with FrameStack wrapper causes invalid actions to be passed to `env.step`
#17
capnspacehook
closed
11 months ago
2
Add DDPG and TD3
#16
araffin
closed
1 year ago
0
[Question] Extending sbx algorithms (e.g via a callback)
#15
asmith26
closed
1 year ago
2
[Enhancement] Support for large gradient_steps in SAC
#14
LabChameleon
closed
8 months ago
2
SAC7
#13
araffin
opened
1 year ago
0
[Question] is it possible cython use this sbx?
#12
diybl
closed
1 year ago
4
Basic dict obs support
#11
araffin
closed
1 year ago
0
Switch to `pyproject.toml`, `ruff`, upgrade SB3
#10
araffin
closed
1 year ago
0
[Bug] example supplied in readme crashing
#9
Robokan
closed
6 months ago
4
crash when using a custom network architecture
#8
Robokan
closed
8 months ago
4
Implement DQN
#7
araffin
closed
1 year ago
0
Implement PPO
#6
araffin
closed
1 year ago
0
Add Qf learning rate param
#5
araffin
closed
1 year ago
0
Implements Feature Extractors
#4
joaogui1
opened
1 year ago
0
Next