issues
search
vincekurtz
/
rddp
Reward-Driven Diffusion Policy
1
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Policy helper class
#23
vincekurtz
closed
1 month ago
0
Big refactor for speed
#22
vincekurtz
closed
1 month ago
0
Add cart pole example
#21
vincekurtz
closed
2 months ago
0
Enforce input limits
#20
vincekurtz
closed
2 months ago
0
Condition on images or image features
#19
vincekurtz
opened
2 months ago
0
PPO baseline for the bug-trap
#18
vincekurtz
closed
2 months ago
0
Automate baselines
#17
vincekurtz
opened
2 months ago
0
Use Brax backend
#16
vincekurtz
closed
2 months ago
0
Anneal the temperature along with the noise level
#15
vincekurtz
closed
2 months ago
0
Bug trap example
#14
vincekurtz
closed
2 months ago
0
Condition policy on output, not state
#13
vincekurtz
closed
3 months ago
0
Observation conditioning
#12
vincekurtz
closed
3 months ago
0
Example Wishlist
#11
vincekurtz
opened
3 months ago
0
Improve the training procedure
#10
vincekurtz
opened
3 months ago
0
CNN-based score model
#9
vincekurtz
opened
3 months ago
0
MJX system template
#8
vincekurtz
closed
2 months ago
1
Unify tools across various examples
#7
vincekurtz
opened
3 months ago
0
Pendulum swingup example
#6
vincekurtz
closed
3 months ago
0
Add a simple double integrator example
#5
vincekurtz
closed
3 months ago
0
Use HDF5 format for saving and dataloading
#4
vincekurtz
closed
3 months ago
0
Train from multiple initial states
#3
vincekurtz
closed
3 months ago
0
Animate reach-avoid solutions
#2
vincekurtz
closed
3 months ago
0
Make noise schedule indpendent of num steps
#1
vincekurtz
closed
3 months ago
0