issues
search
coax-dev
/
coax
Modular framework for Reinforcement Learning in python
https://coax.readthedocs.io
MIT License
168
stars
17
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Example of using this lib for RLHF?
#41
asmith26
opened
1 year ago
0
Switch to Gymnasium
#40
KristianHolsheimer
closed
1 year ago
0
Gymnasium Support
#39
arjun-prakash
closed
1 year ago
3
Changed assertion in generate_gif to check on returned datatype
#38
pixelsandpointers
closed
1 year ago
1
DQN pong example doesn't work off the shelf
#37
thisiscam
closed
1 year ago
4
Fix docs toc and bump version
#36
KristianHolsheimer
closed
1 year ago
1
Switch to new Google Analytics tracking ID.
#35
KristianHolsheimer
closed
1 year ago
0
Recurrent Experience Replay
#34
smorad
opened
2 years ago
3
Docs side bar contains low-level entries
#33
KristianHolsheimer
opened
2 years ago
0
Fix 31: Update gym signatures in Frozen Lake
#32
dbleyl
closed
2 years ago
2
Frozen Lake example has an invalid gym signature.
#31
dbleyl
closed
2 years ago
3
MiniMax Algorithm?
#30
flaport
opened
2 years ago
1
Add DeepMind Control Suite Example
#29
frederikschubert
closed
2 years ago
6
Update to gym==0.26.x
#28
frederikschubert
closed
2 years ago
3
Update to new Jax API
#27
frederikschubert
closed
2 years ago
0
Add dm_control example for SAC
#26
frederikschubert
closed
2 years ago
4
use list for simple replay buffer
#25
frederikschubert
closed
2 years ago
1
fix random_seed in _prioritized
#24
tytsao
closed
2 years ago
1
Sharing parameters between actor and critic?
#23
mhr
closed
2 years ago
1
Fix multidiscrete preprocessor
#22
KristianHolsheimer
closed
2 years ago
0
Assertion assert_equal_shape failed for MultiDiscrete action space
#21
xiangyuy
closed
2 years ago
5
Incorporating jax.jit into a customer policy
#20
UweGensheimer
closed
2 years ago
3
upgrade dependencies
#19
KristianHolsheimer
closed
2 years ago
0
Implementation of StochasticQ in ClippedDoubleQLearning
#18
frederikschubert
closed
2 years ago
2
fix default preprocessor for MultiDiscrete space
#17
KristianHolsheimer
closed
2 years ago
0
'linear/w' does not match shape
#16
bcerjan
closed
2 years ago
5
WIP: add type annotations
#15
frederikschubert
closed
2 years ago
0
Convert Numpy Docstrings to Google Style
#14
frederikschubert
opened
2 years ago
0
Add Type Annotations
#13
frederikschubert
opened
2 years ago
0
Fix NStepEntropyRegularizer
#12
frederikschubert
closed
2 years ago
1
Fix Regularization in SAC
#11
frederikschubert
closed
2 years ago
0
Clean up license.
#10
KristianHolsheimer
closed
2 years ago
0
Implement StochasticQ for ClippedDoubleQLearning
#9
frederikschubert
closed
2 years ago
0
Refactoring of ClippedDoubleQLearning for DSAC
#8
frederikschubert
closed
3 years ago
12
Multi-Step Entropy Regularization for SAC
#7
frederikschubert
closed
3 years ago
3
Implementation of SAC
#6
frederikschubert
closed
3 years ago
3
PPOClip grad update seems to cause inf update
#5
glmcdona
opened
3 years ago
3
Quantile Q-Learning Implementation
#4
frederikschubert
closed
3 years ago
11
Implementation of Implicit Quantile Networks
#3
frederikschubert
closed
3 years ago
1
AttributeError: module 'jax.api' has no attribute '_jit_is_disabled'
#2
mmcaulif
closed
3 years ago
3
Logging interval for Tensorboard
#1
dandelin
closed
3 years ago
2