Data Augmentation¶
d3rlpy provides data augmentation techniques tightly integrated with reinforcement learning algorithms.
Efficient data augmentation potentially boosts algorithm performance significantly.
from d3rlpy.algos import DiscreteCQL
# choose data augmentation types
cql = DiscreteCQL(augmentation=['random_shift', 'intensity'])
You can also tune data augmentation parameters by yourself.
from d3rlpy.augmentation.image import RandomShift
random_shift = RandomShift(shift_size=10)
cql = DiscreteCQL(augmentation=[random_shift, 'intensity'])
Image Observation¶
Random shift augmentation. |
|
Cutout augmentation. |
|
Horizontal flip augmentation. |
|
Vertical flip augmentation. |
|
Random rotation augmentation. |
|
Intensity augmentation. |
|
Color Jitter augmentation. |
Vector Observation¶
Single Amplitude Scaling augmentation. |
|
Multiple Amplitude Scaling augmentation. |
Augmentation Pipeline¶
Data-reguralized Q augmentation pipeline. |