mirror of
https://github.com/gryf/coach.git
synced 2025-12-18 19:50:17 +01:00
0896f43097
* Add Robosuite parameters for all env types + initialize env flow * Init flow done * Rest of Environment API complete for RobosuiteEnvironment * RobosuiteEnvironment changes * Observation stacking filter * Add proper frame_skip in addition to control_freq * Hardcode Coach rendering to 'frontview' camera * Robosuite_Lift_DDPG preset + Robosuite env updates * Move observation stacking filter from env to preset * Pre-process observation - concatenate depth map (if exists) to image and object state (if exists) to robot state * Preset parameters based on Surreal DDPG parameters, taken from: https://github.com/SurrealAI/surreal/blob/master/surreal/main/ddpg_configs.py * RobosuiteEnvironment fixes - working now with PyGame rendering * Preset minor modifications * ObservationStackingFilter - option to concat non-vector observations * Consider frame skip when setting horizon in robosuite env * Robosuite lift preset - update heatup length and training interval * Robosuite env - change control_freq to 10 to match Surreal usage * Robosuite clipped PPO preset * Distribute multiple workers (-n #) over multiple GPUs * Clipped PPO memory optimization from @shadiendrawis * Fixes to evaluation only workers * RoboSuite_ClippedPPO: Update training interval * Undo last commit (update training interval) * Fix "doube-negative" if conditions * multi-agent single-trainer clipped ppo training with cartpole * cleanups (not done yet) + ~tuned hyper-params for mast * Switch to Robosuite v1 APIs * Change presets to IK controller * more cleanups + enabling evaluation worker + better logging * RoboSuite_Lift_ClippedPPO updates * Fix major bug in obs normalization filter setup * Reduce coupling between Robosuite API and Coach environment * Now only non task-specific parameters are explicitly defined in Coach * Removed a bunch of enums of Robosuite elements, using simple strings instead * With this change new environments/robots/controllers in Robosuite can be used immediately in Coach * MAST: better logging of actor-trainer interaction + bug fixes + performance improvements. Still missing: fixed pubsub for obs normalization running stats + logging for trainer signals * lstm support for ppo * setting JOINT VELOCITY action space by default + fix for EveryNEpisodes video dump filter + new TaskIDDumpFilter + allowing or between video dump filters * Separate Robosuite clipped PPO preset for the non-MAST case * Add flatten layer to architectures and use it in Robosuite presets This is required for embedders that mix conv and dense TODO: Add MXNet implementation * publishing running_stats together with the published policy + hyper-param for when to publish a policy + cleanups * bug-fix for memory leak in MAST * Bugfix: Return value in TF BatchnormActivationDropout.to_tf_instance * Explicit activations in embedder scheme so there's no ReLU after flatten * Add clipped PPO heads with configurable dense layers at the beginning * This is a workaround needed to mimic Surreal-PPO, where the CNN and LSTM are shared between actor and critic but the FC layers are not shared * Added a "SchemeBuilder" class, currently only used for the new heads but we can change Middleware and Embedder implementations to use it as well * Video dump setting fix in basic preset * logging screen output to file * coach to start the redis-server for a MAST run * trainer drops off-policy data + old policy in ClippedPPO updates only after policy was published + logging free memory stats + actors check for a new policy only at the beginning of a new episode + fixed a bug where the trainer was logging "Training Reward = 0", causing dashboard to incorrectly display the signal * Add missing set_internal_state function in TFSharedRunningStats * Robosuite preset - use SingleLevelSelect instead of hard-coded level * policy ID published directly on Redis * Small fix when writing to log file * Major bugfix in Robosuite presets - pass dense sizes to heads * RoboSuite_Lift_ClippedPPO hyper-params update * add horizon and value bootstrap to GAE calculation, fix A3C with LSTM * adam hyper-params from mujoco * updated MAST preset with IK_POSE_POS controller * configurable initialization for policy stdev + custom extra noise per actor + logging of policy stdev to dashboard * values loss weighting of 0.5 * minor fixes + presets * bug-fix for MAST where the old policy in the trainer had kept updating every training iter while it should only update after every policy publish * bug-fix: reset_internal_state was not called by the trainer * bug-fixes in the lstm flow + some hyper-param adjustments for CartPole_ClippedPPO_LSTM -> training and sometimes reaches 200 * adding back the horizon hyper-param - a messy commit * another bug-fix missing from prev commit * set control_freq=2 to match action_scale 0.125 * ClippedPPO with MAST cleanups and some preps for TD3 with MAST * TD3 presets. RoboSuite_Lift_TD3 seems to work well with multi-process runs (-n 8) * setting termination on collision to be on by default * bug-fix following prev-prev commit * initial cube exploration environment with TD3 commit * bug fix + minor refactoring * several parameter changes and RND debugging * Robosuite Gym wrapper + Rename TD3_Random* -> Random* * algorithm update * Add RoboSuite v1 env + presets (to eventually replace non-v1 ones) * Remove grasping presets, keep only V1 exp. presets (w/o V1 tag) * Keep just robosuite V1 env as the 'robosuite_environment' module * Exclude Robosuite and MAST presets from integration tests * Exclude LSTM and MAST presets from golden tests * Fix mistakenly removed import * Revert debug changes in ReaderWriterLock * Try another way to exclude LSTM/MAST golden tests * Remove debug prints * Remove PreDense heads, unused in the end * Missed removing an instance of PreDense head * Remove MAST, not required for this PR * Undo unused concat option in ObservationStackingFilter * Remove LSTM updates, not required in this PR * Update README.md * code changes for the exploration flow to work with robosuite master branch * code cleanup + documentation * jupyter tutorial for the goal-based exploration + scatter plot * typo fix * Update README.md * seprate parameter for the obs-goal observation + small fixes * code clarity fixes * adjustment in tutorial 5 * Update tutorial * Update tutorial Co-authored-by: Guy Jacob <guy.jacob@intel.com> Co-authored-by: Gal Leibovich <gal.leibovich@intel.com> Co-authored-by: shadi.endrawis <sendrawi@aipg-ra-skx-03.ra.intel.com>
86 lines
2.3 KiB
Python
86 lines
2.3 KiB
Python
# nasty hack to deal with issue #46
|
|
import os
|
|
import sys
|
|
|
|
sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(__file__))))
|
|
|
|
import pytest
|
|
import os
|
|
import time
|
|
import shutil
|
|
from subprocess import Popen, DEVNULL
|
|
from rl_coach.logger import screen
|
|
|
|
FAILING_PRESETS = [
|
|
'Fetch_DDPG_HER_baselines',
|
|
'MontezumaRevenge_BC',
|
|
'ControlSuite_DDPG',
|
|
'Doom_Basic_BC',
|
|
'CARLA_CIL',
|
|
'CARLA_DDPG',
|
|
'CARLA_Dueling_DDQN',
|
|
'CARLA_3_Cameras_DDPG',
|
|
'Starcraft_CollectMinerals_A3C',
|
|
'Starcraft_CollectMinerals_Dueling_DDQN',
|
|
'RoboSuite_CubeExp_Random',
|
|
'RoboSuite_CubeExp_TD3_Goal_Based',
|
|
'RoboSuite_CubeExp_TD3_Intrinsic_Reward',
|
|
]
|
|
|
|
def all_presets():
|
|
result = []
|
|
for f in sorted(os.listdir('rl_coach/presets')):
|
|
if f.endswith('.py') and f != '__init__.py':
|
|
preset = f.split('.')[0]
|
|
if preset not in FAILING_PRESETS:
|
|
result.append(preset)
|
|
return result
|
|
|
|
|
|
@pytest.fixture(params=all_presets())
|
|
def preset(request):
|
|
return request.param
|
|
|
|
|
|
@pytest.mark.integration_test
|
|
def test_preset_runs(preset):
|
|
test_failed = False
|
|
|
|
print("Testing preset {}".format(preset))
|
|
|
|
# TODO: this is a temporary workaround for presets which define more than a single available level.
|
|
# we should probably do this in a more robust way
|
|
level = ""
|
|
if "Atari" in preset:
|
|
level = "breakout"
|
|
elif "Mujoco" in preset:
|
|
level = "inverted_pendulum"
|
|
elif "ControlSuite" in preset:
|
|
level = "pendulum:swingup"
|
|
|
|
experiment_name = ".test-" + preset
|
|
|
|
# overriding heatup steps to some small number of steps (1000), so to finish the heatup stage, and get to train
|
|
params = ["python3", "rl_coach/coach.py", "-p", preset, "-ns", "-e", experiment_name, '-cp',
|
|
'heatup_steps=EnvironmentSteps(1000)']
|
|
if level != "":
|
|
params += ["-lvl", level]
|
|
|
|
p = Popen(params)
|
|
|
|
# wait 30 seconds overhead of initialization, and finishing heatup.
|
|
time.sleep(30)
|
|
return_value = p.poll()
|
|
|
|
if return_value is None:
|
|
screen.success("{} passed successfully".format(preset))
|
|
else:
|
|
test_failed = True
|
|
screen.error("{} failed".format(preset), crash=False)
|
|
|
|
p.kill()
|
|
if os.path.exists("experiments/" + experiment_name):
|
|
shutil.rmtree("experiments/" + experiment_name)
|
|
|
|
assert not test_failed
|