ydy0615/lerobot-clone
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-06-03 04:11:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(rl): correctly wire HIL-SERL gripper penalty through processor pipeline

Browse Source 
(cherry picked from commit 9c2af818ff)
This commit is contained in:
Khalil Meftah
2026-04-26 16:36:21 +02:00
parent 38b88c414c
commit 356a64d8c4
2 changed files with 51 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
src/lerobot/processor/hil_processor.py
View File

@@ -321,6 +321,7 @@ class GymHILAdapterProcessorStep(ProcessorStep):
This step normalizes the `transition` object by:
1. Copying `teleop_action` from `info` to `complementary_data`.
2. Copying `is_intervention` from `info` (using the string key) to `info` (using the enum key).
3. Copying `discrete_penalty` from `info` to `complementary_data`.
"""
def __call__(self, transition: EnvTransition) -> EnvTransition:
@@ -330,6 +331,9 @@ class GymHILAdapterProcessorStep(ProcessorStep):
if TELEOP_ACTION_KEY in info:
complementary_data[TELEOP_ACTION_KEY] = info[TELEOP_ACTION_KEY]
if DISCRETE_PENALTY_KEY in info:
complementary_data[DISCRETE_PENALTY_KEY] = info[DISCRETE_PENALTY_KEY]
if "is_intervention" in info:
info[TeleopEvents.IS_INTERVENTION] = info["is_intervention"]
@@ -348,18 +352,24 @@ class GymHILAdapterProcessorStep(ProcessorStep):
@ProcessorStepRegistry.register("gripper_penalty_processor")
class GripperPenaltyProcessorStep(ProcessorStep):
"""
Applies a penalty for inefficient gripper usage.
Applies a small per-transition cost on the discrete gripper action.
This step penalizes actions that attempt to close an already closed gripper or
open an already open one, based on position thresholds.
Fires only when the commanded action would actually transition the gripper
from one extreme to the other (close-while-open or open-while-closed).
This discourages gripper oscillation while leaving "stay" and saturating-further
commands unpenalized.
Attributes:
penalty: The negative reward value to apply.
max_gripper_pos: The maximum position value for the gripper, used for normalization.
open_threshold: Normalized state below which the gripper is considered "open".
closed_threshold: Normalized state above which the gripper is considered "closed".
"""
penalty: float = -0.01
penalty: float = -0.02
max_gripper_pos: float = 30.0
open_threshold: float = 0.1
closed_threshold: float = 0.9
def __call__(self, transition: EnvTransition) -> EnvTransition:
"""
@@ -391,9 +401,13 @@ class GripperPenaltyProcessorStep(ProcessorStep):
gripper_state_normalized = current_gripper_pos / self.max_gripper_pos
# Calculate penalty boolean as in original
gripper_penalty_bool = (gripper_state_normalized < 0.5 and gripper_action_normalized > 0.5) or (
gripper_state_normalized > 0.75 and gripper_action_normalized < 0.5
)
# - currently open AND target is closed -> close transition
# - currently closed AND target is open -> open transition
is_open = gripper_state_normalized < self.open_threshold
is_closed = gripper_state_normalized > self.closed_threshold
cmd_close = gripper_action_normalized > self.closed_threshold
cmd_open = gripper_action_normalized < self.open_threshold
gripper_penalty_bool = (is_open and cmd_close) or (is_closed and cmd_open)
gripper_penalty = self.penalty * int(gripper_penalty_bool)
@@ -409,11 +423,14 @@ class GripperPenaltyProcessorStep(ProcessorStep):
Returns the configuration of the step for serialization.
Returns:
A dictionary containing the penalty value and max gripper position.
A dictionary containing the penalty value, max gripper position,
and the open/closed thresholds.
"""
return {
"penalty": self.penalty,
"max_gripper_pos": self.max_gripper_pos,
"open_threshold": self.open_threshold,
"closed_threshold": self.closed_threshold,
}
def reset(self) -> None: