mirror of
https://github.com/huggingface/lerobot.git
synced 2026-08-08 17:39:44 +00:00
e963e5a0c4
* refactor: RL stack refactoring — RLAlgorithm, RLTrainer, DataMixer, and SAC restructuring
* chore: clarify torch.compile disabled note in SACAlgorithm
* fix(teleop): keyboard EE teleop not registering special keys and losing intervention state
Fixes #2345
Co-authored-by: jpizarrom <jpizarrom@gmail.com>
* fix: remove leftover normalization calls from reward classifier predict_reward
Fixes #2355
* fix: add thread synchronization to ReplayBuffer to prevent race condition between add() and sample()
* refactor: update SACAlgorithm to pass action_dim to _init_critics and fix encoder reference
* perf: remove redundant CPU→GPU→CPU transition move in learner
* Fix: add kwargs in reward classifier __init__()
* fix: include IS_INTERVENTION in complementary_info sent to learner for offline replay buffer
* fix: add try/finally to control_loop to ensure image writer cleanup on exit
* fix: use string key for IS_INTERVENTION in complementary_info to avoid torch.load serialization error
* fix: skip tests that require grpc if not available
* fix(tests): ensure tensor stats comparison accounts for reshaping in normalization tests
* fix(tests): skip tests that require grpc if not available
* refactor(rl): expose public API in rl/__init__ and use relative imports in sub-packages
* fix(config): update vision encoder model name to lerobot/resnet10
* fix(sac): clarify torch.compile status
* refactor(rl): update shutdown_event type hints from 'any' to 'Any' for consistency and clarity
* refactor(sac): simplify optimizer return structure
* perf(rl): use async iterators in OnlineOfflineMixer.get_iterator
* refactor(sac): decouple algorithm hyperparameters from policy config
* update losses names in tests
* fix docstring
* remove unused type alias
* fix test for flat dict structure
* refactor(policies): rename policies/sac → policies/gaussian_actor
* refactor(rl/sac): consolidate hyperparameter ownership and clean up discrete critic
* perf(observation_processor): add CUDA support for image processing
* fix(rl): correctly wire HIL-SERL gripper penalty through processor pipeline
(cherry picked from commit 9c2af818ff4bfef2603348e0609aa249c3ff62b1)
* fix(rl): add time limit processor to environment pipeline
(cherry picked from commit cd105f65cb213c4a9c9768926cc3304ca52eb5f4)
* fix(rl): clarify discrete gripper action mapping in GripperVelocityToJoint for SO100
(cherry picked from commit 494f469a2b9dfb792dde6d9d79d8646ef4fcff54)
* fix(rl): update neutral gripper action
(cherry picked from commit 9c9064e5befe82e981286c6562194f524e16045e)
* fix(rl): merge environment and action-processor info in transition processing
(cherry picked from commit 30e1886b6466b8753ec41b3016c09a17dd3e960b)
* fix(rl): mirror gym_manipulator in actor
(cherry picked from commit d2a046dfc5b6f79df34577aa45f32403d897c0a3)
* fix(rl): postprocess action in actor
(cherry picked from commit c2556439e550ee3fe5bae6060c57cf227101fcaf)
* fix(rl): improve action processing for discrete and continuous actions
(cherry picked from commit f887ab3f6ace140c4ea6b6186c26473d785b0727)
* fix(rl): enhance intervention handling in actor and learner
(cherry picked from commit ef8bfffbd72e9d0951de576553f89c7c281315de)
* Revert "perf(observation_processor): add CUDA support for image processing"
This reverts commit 38b88c414c.
* refactor(rl): make algorithm a nested config so all SAC hyperparameters are JSON-addressable
* refactor(rl): add make_algorithm_config function for RLAlgorithmConfig instantiation
* refactor(rl): add type property to RLAlgorithmConfig for better clarity
* refactor(rl): make RLAlgorithmConfig an abstract base class for better extensibility
* refactor(tests): remove grpc import checks from test files for cleaner code
* fix(tests): gate RL tests on the `datasets` extra
* refactor: simplify docstrings for clarity and conciseness across multiple files
* fix(rl): update gripper position key and handle action absence during reset
* fix(rl): record pre-step observation so (obs, action, next.reward) align in gym_manipulator dataset
* refactor: clean up import statements
* chore: address reviewer comments
* chore: improve visual stats reshaping logic and update docstring for clarity
* refactor: enforce mandatory config_class and name attributes in RLAlgorithm
* refactor: implement NotImplementedError for abstract methods in RLAlgorithm and DataMixer
* refactor: replace build_algorithm with make_algorithm for SACAlgorithmConfig and update related tests
* refactor: add require_package calls for grpcio and gym-hil in relevant modules
* refactor(rl): move grpcio guards to runtime entry points
* feat(rl): consolidate HIL-SERL checkpoint into HF-style components
Make `RLAlgorithmConfig` and `RLAlgorithm` `HubMixin`s, add abstract
`state_dict()` / `load_state_dict()` for critic ensemble, target nets
and `log_alpha`, and persist them as a sibling `algorithm/` component
next to `pretrained_model/`. Replace the pickled `training_state.pt`
with an enriched `training_step.json` carrying `step` and
`interaction_step`, so resume restores actor + critics + target nets +
temperature + optimizers + RNG + counters from HF-standard files.
* refactor(rl): move actor weight-sync wire format from policy to algorithm
* refactor(rl): update type hints for learner and actor functions
* refactor(rl): hoist grpcio guard to module top in actor/learner
* chore(rl): manage import pattern in actor (#3564)
* chore(rl): manage import pattern in actor
* chore(rl): optional grpc imports in learner; quote grpc ServicerContext types
---------
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
* update uv.lock
* chore(doc): update doc
---------
Co-authored-by: jpizarrom <jpizarrom@gmail.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
115 lines
3.8 KiB
Python
115 lines
3.8 KiB
Python
#!/usr/bin/env python
|
|
|
|
# Copyright 2025 The HuggingFace Inc. team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import multiprocessing
|
|
import os
|
|
import signal
|
|
import threading
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
pytest.importorskip("datasets", reason="datasets is required (install lerobot[dataset])")
|
|
|
|
from lerobot.utils.process import ProcessSignalHandler # noqa: E402
|
|
|
|
|
|
# Fixture to reset shutdown_event_counter and original signal handlers before and after each test
|
|
@pytest.fixture(autouse=True)
|
|
def reset_globals_and_handlers():
|
|
# Store original signal handlers
|
|
original_handlers = {
|
|
sig: signal.getsignal(sig)
|
|
for sig in [signal.SIGINT, signal.SIGTERM, signal.SIGHUP, signal.SIGQUIT]
|
|
if hasattr(signal, sig.name)
|
|
}
|
|
|
|
yield
|
|
|
|
# Restore original signal handlers
|
|
for sig, handler in original_handlers.items():
|
|
signal.signal(sig, handler)
|
|
|
|
|
|
def test_setup_process_handlers_event_with_threads():
|
|
"""Test that setup_process_handlers returns the correct event type."""
|
|
handler = ProcessSignalHandler(use_threads=True)
|
|
shutdown_event = handler.shutdown_event
|
|
assert isinstance(shutdown_event, threading.Event), "Should be a threading.Event"
|
|
assert not shutdown_event.is_set(), "Event should initially be unset"
|
|
|
|
|
|
def test_setup_process_handlers_event_with_processes():
|
|
"""Test that setup_process_handlers returns the correct event type."""
|
|
handler = ProcessSignalHandler(use_threads=False)
|
|
shutdown_event = handler.shutdown_event
|
|
assert isinstance(shutdown_event, type(multiprocessing.Event())), "Should be a multiprocessing.Event"
|
|
assert not shutdown_event.is_set(), "Event should initially be unset"
|
|
|
|
|
|
@pytest.mark.parametrize("use_threads", [True, False])
|
|
@pytest.mark.parametrize(
|
|
"sig",
|
|
[
|
|
signal.SIGINT,
|
|
signal.SIGTERM,
|
|
# SIGHUP and SIGQUIT are not reliably available on all platforms (e.g. Windows)
|
|
pytest.param(
|
|
signal.SIGHUP,
|
|
marks=pytest.mark.skipif(not hasattr(signal, "SIGHUP"), reason="SIGHUP not available"),
|
|
),
|
|
pytest.param(
|
|
signal.SIGQUIT,
|
|
marks=pytest.mark.skipif(not hasattr(signal, "SIGQUIT"), reason="SIGQUIT not available"),
|
|
),
|
|
],
|
|
)
|
|
def test_signal_handler_sets_event(use_threads, sig):
|
|
"""Test that the signal handler sets the event on receiving a signal."""
|
|
handler = ProcessSignalHandler(use_threads=use_threads)
|
|
shutdown_event = handler.shutdown_event
|
|
|
|
assert handler.counter == 0
|
|
|
|
os.kill(os.getpid(), sig)
|
|
|
|
# In some environments, the signal might take a moment to be handled.
|
|
shutdown_event.wait(timeout=1.0)
|
|
|
|
assert shutdown_event.is_set(), f"Event should be set after receiving signal {sig}"
|
|
|
|
# Ensure the internal counter was incremented
|
|
assert handler.counter == 1
|
|
|
|
|
|
@pytest.mark.parametrize("use_threads", [True, False])
|
|
@patch("sys.exit")
|
|
def test_force_shutdown_on_second_signal(mock_sys_exit, use_threads):
|
|
"""Test that a second signal triggers a force shutdown."""
|
|
handler = ProcessSignalHandler(use_threads=use_threads)
|
|
|
|
os.kill(os.getpid(), signal.SIGINT)
|
|
# Give a moment for the first signal to be processed
|
|
import time
|
|
|
|
time.sleep(0.1)
|
|
os.kill(os.getpid(), signal.SIGINT)
|
|
|
|
time.sleep(0.1)
|
|
|
|
assert handler.counter == 2
|
|
mock_sys_exit.assert_called_once_with(1)
|