issues
search
rail-berkeley
/
rlkit
Collection of reinforcement learning algorithms
MIT License
2.45k
stars
550
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Copy vs Deepcopy in SAC
#74
richardrl
opened
5 years ago
4
SAC policy loss
#73
rmrafailov
closed
5 years ago
1
Use torch.load in run_policy
#72
mihaic
closed
5 years ago
0
Alpha loss bug?
#71
KeAWang
closed
5 years ago
1
unable to test the learnt model because customed_goal_sampler is not loaded
#70
ZiwenZhuang
opened
5 years ago
5
where is the skew-fit coresponding code
#69
ZiwenZhuang
closed
5 years ago
4
This commit fixes #67
#68
vuoristo
closed
5 years ago
0
Loading checkpoint trained on GPU on a CPU device fails.
#67
vuoristo
closed
5 years ago
6
Added linear scheduling option to epsilon greedy exploration
#66
cdevin
opened
5 years ago
0
Added linear scheduling option to epsilon greedy exploration
#65
cdevin
closed
5 years ago
1
FetchReach her example fails - easy to fix though
#64
MishaLaskin
closed
4 years ago
1
Some benchmarks on six MuJoCo-v2 environments for DDPG and TD3
#63
DanielTakeshi
opened
5 years ago
3
Exception has occurred: AssertionError with Gym v0.12
#62
AndrewPaulChester
closed
5 years ago
2
install multiworld
#61
dwiel
closed
5 years ago
0
dependency on multiworld even when not using it
#60
dwiel
closed
5 years ago
4
Compatibility with pytorch 1.0
#59
nm-narasimha
closed
5 years ago
2
DDPG example - Missing TorchRLAlgorithm, how to use BatchRLDatasetAlgorithm
#58
nm-narasimha
closed
5 years ago
1
Update multiworld env registration in pickup_goal_dataset.py
#57
anair13
closed
5 years ago
0
OSError: [Errno 12] Cannot allocate memory
#56
cww97
closed
5 years ago
2
Multitask environment file does not exist
#55
ghost
closed
5 years ago
7
Dataset based Trainer
#54
redknightlois
opened
5 years ago
5
Investigate super-convergence on RL algorithms
#53
redknightlois
opened
5 years ago
4
Memory Mapped based replay buffer
#52
redknightlois
opened
5 years ago
1
Eval statistics for SAC
#51
amandlek
closed
5 years ago
2
[Question] Any idea why SAC loss would diverge?
#50
redknightlois
closed
5 years ago
8
SAC HER example results not matching
#49
Shade5
closed
5 years ago
7
Make sure you dont need a Mujoco license to use any of the algorithms
#48
redknightlois
closed
5 years ago
5
Numpy to Pytorch should ignore Pytorch Tensors
#47
redknightlois
closed
5 years ago
5
HOME does not exist on Windows
#46
redknightlois
closed
5 years ago
2
while pass ‘render=True’ get 'Window rendering not supported'
#45
cww97
closed
5 years ago
2
how can I render while training
#44
cww97
closed
5 years ago
1
Future entropy missed in SAC.
#43
brickerino
closed
5 years ago
4
Add online rl algorithm + train_mode function
#42
hexiang-hu
closed
5 years ago
3
Performance on Hopper-v2
#41
quanvuong
closed
5 years ago
11
Value network in TwinSAC
#40
jendelel
closed
5 years ago
3
snapshot model weights and optionally load pre-trained weights before training
#39
katerakelly
closed
5 years ago
0
The policy loss in SAC?
#38
zhaoyingnan179346
closed
5 years ago
1
Use stable implementation of tanh's inverse log determinant Jacobian
#37
alexlee-gk
closed
5 years ago
1
Training env is reset at start of epoch, but PathBuilder not reset. Resulting in erroneous Exploration statistics.
#36
pimdh
closed
5 years ago
4
Features/openai hacks
#35
richardrl
opened
5 years ago
1
ImportError: No module named 'glfw'
#34
tseyde
opened
5 years ago
8
best way to resume training from PKL
#33
richardrl
opened
5 years ago
11
HER DQN enabled, along with example code running on gridworld.
#32
cdevin
closed
5 years ago
0
Cannot learn (pusher experiment)
#31
Nicolas99-9
opened
5 years ago
10
Unable to reproduce the results of HER-TD3
#30
charliezon
closed
5 years ago
6
removed extraneous full_observation appendage
#29
richardrl
closed
5 years ago
0
Support discrete action in HER replay buffer
#28
vitchyr
closed
5 years ago
1
Multiple worker support
#27
richardrl
opened
5 years ago
10
Retrieve s3
#26
richardrl
closed
5 years ago
1
Making local mode Not run through doodad
#25
richardrl
closed
5 years ago
2
Previous
Next