mirror of
https://github.com/huggingface/lerobot.git
synced 2026-07-23 09:46:00 +00:00
hls_gaus true
This commit is contained in:
@@ -57,7 +57,7 @@ class RLearNConfig(PreTrainedConfig):
|
|||||||
num_register_tokens: int = 4
|
num_register_tokens: int = 4
|
||||||
|
|
||||||
# --- reward head options ---
|
# --- reward head options ---
|
||||||
use_categorical_rewards: bool = True # classification over bins
|
use_categorical_rewards: bool = False # classification over bins
|
||||||
num_reward_bins: int = 25
|
num_reward_bins: int = 25
|
||||||
reward_min_value: float = 0.0 # for HL-Gauss range
|
reward_min_value: float = 0.0 # for HL-Gauss range
|
||||||
reward_max_value: float = 1.0
|
reward_max_value: float = 1.0
|
||||||
@@ -65,7 +65,7 @@ class RLearNConfig(PreTrainedConfig):
|
|||||||
hl_gauss_num_bins: int = 25 # histogram resolution
|
hl_gauss_num_bins: int = 25 # histogram resolution
|
||||||
|
|
||||||
# Inference-time subsampling and regularization
|
# Inference-time subsampling and regularization
|
||||||
inference_stride: int = 1 # in forward
|
inference_stride: int = 1 # inference_stride is an extra, second downsampling applied in forward after window sampling/rewind. Keep it at 1 to disable extra skipping
|
||||||
frame_dropout_p: float = 0.10
|
frame_dropout_p: float = 0.10
|
||||||
|
|
||||||
# Training
|
# Training
|
||||||
|
|||||||
Reference in New Issue
Block a user