issues
search
rail-berkeley
/
rlkit
Collection of reinforcement learning algorithms
MIT License
2.52k
stars
553
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Default GPU Yaml file fails
#124
richardrl
opened
4 years ago
4
Code for generating results figures?
#123
avandekleut
opened
4 years ago
1
AWACTrainer is just an implementation of AWR algorithm?
#122
vinowan
closed
4 years ago
0
Visualizing the Training and Running the Trained Policy using RIG
#121
amir-ramezani-ai
opened
4 years ago
6
Add missing __init__.py file
#120
shuternay
closed
4 years ago
0
MSE reconstruction loss in VAE training is summed over, not averaged over
#119
mseitzer
closed
4 years ago
3
Why is goal_sampling_mode='vae_prior' in Skew-Fits sawyer_push config?
#118
mseitzer
closed
4 years ago
2
New tag for version before AWAC commit
#117
ksluck
closed
4 years ago
2
minor fix DQN
#116
st2yang
closed
4 years ago
0
AWAC implementation
#115
anair13
closed
4 years ago
2
Fix for DQN and DDQN target network update
#114
harshakokel
closed
4 years ago
1
Corrected SAC get_snapshot.
#113
IanChar
closed
4 years ago
1
More efficient future obs sample method in obs_dict_replay_buffer.py
#112
YangRui2015
closed
4 years ago
4
Change sampling method from randint to choice in Replay and robustify policy networks in SAC
#111
ksluck
closed
4 years ago
3
Introducing possibility to change the standard alpha parameter for SAC
#110
ksluck
closed
4 years ago
0
Optimize actor before the critic
#109
Xingyu-Lin
closed
4 years ago
1
How to log performance metrics when evaluating a trained policy?
#108
PierreExeter
closed
4 years ago
2
[solved] ResolvePackageNotFound error when installing the conda environment
#107
PierreExeter
closed
4 years ago
1
launch different seeds simulateously
#106
ChenyangRan
opened
4 years ago
4
Pets
#105
virajmehta
closed
4 years ago
0
Skew fit on non visual based environments?
#104
thibautlavril
opened
4 years ago
0
Can't run trained policy because there's an issue with loading the models.
#103
MhmdGaffar
closed
4 years ago
0
Issue with reproducibility
#102
RushikeshJoshi4
closed
4 years ago
2
Trying to run_policy.py while also run_sac.py
#101
nanbaima
closed
4 years ago
1
couldn't find the core code file that implements "Skew-Fit".
#100
COST-97
closed
4 years ago
1
key error when run_policy
#99
ChenyangRan
closed
4 years ago
4
Data overwritten in multitask_rollout
#98
HeinzBenjamin
closed
4 years ago
4
Unusual MountainCarContinuous Results
#97
xxmissingnoxx
closed
4 years ago
4
Incomplete relabelling of trajectories in HER
#96
rstrudel
closed
4 years ago
5
How to deal with not converging with HER_SAC
#95
YunchuZhang
opened
4 years ago
0
about cuda error during replay weight
#94
YunchuZhang
closed
4 years ago
9
"Forgetting Learning" using SAC in a Drone environment on PyRep
#93
kaelgabriel
opened
4 years ago
2
UnicodeEncodeError
#92
invisilmk
opened
4 years ago
3
No value function in Soft Actor Critic?
#91
KK666-AI
closed
4 years ago
1
Cannot render custom Gym environment "TypeError: 'bool' object is not callable"
#90
PierreExeter
closed
4 years ago
3
Understanding the SAC paramters
#89
nanbaima
closed
4 years ago
2
Difference bewteen creating environments by different methods
#88
wayunderfoot
closed
4 years ago
2
why used two q function in sac?
#87
KK666-AI
closed
5 years ago
1
seeds args in SAC
#86
wayunderfoot
closed
5 years ago
1
question about the seed args
#85
wayunderfoot
closed
5 years ago
4
self.custom_goal_sample is None
#84
Jingjinganhao
closed
4 years ago
3
'ConvVAE' object has no attribute '__name__'
#83
hieubkset
closed
4 years ago
3
General understanding: Purpose of evaluation in training
#82
HeinzBenjamin
closed
5 years ago
1
SAC - can't pickle _thread.RLock objects
#81
cambel
closed
5 years ago
3
Having SkewFit deal with stochastic environments
#80
edessa
closed
5 years ago
2
VAE Reconstructions for Multiple Pucks
#79
edessa
closed
5 years ago
0
Which commit of Doodad is rlkit using?
#78
Xingyu-Lin
closed
5 years ago
3
No data file is being created and filed with new SAC trainings
#77
nanbaima
closed
4 years ago
2
distance in code ???
#76
vitiennam
closed
5 years ago
1
alpha convergence issues with discrete actions
#75
wcarvalho
closed
5 years ago
1
Previous
Next