Closed TPEmist closed 2 years ago
Sorry for the confusing use of --demo_path
. The --demo_path
should contain a prefix of file names, e.g. --demo_path demos/table_lack/Sawyer
. This is designed for the use a partition of demos, e.g. Sawyer_table_lack_0825_0
for part 0 and Sawyer_table_lack_0825_1
for part 1.
with my folder like skill_chaining / demos / table_lack / Sawyer_table_lack_0825_xxx.pkl files In skill_chaining folder I ran:
mpirun -np 4 python3 -m run --algo ppo --furniture_name table_lack_0825 --demo_path demos/table_lack/Sawyer --num_connects 4 --max_episode_steps 800 --max_global_step 200000000 --run_prefix ppo
Still getting error:
Invalid MIT-MAGIC-COOKIE-1 keypybullet build time: Feb 28 2022 22:32:49
pybullet build time: Feb 28 2022 22:32:49
/usr/local/lib/python3.8/dist-packages/ale_py/roms/__init__.py:94: DeprecationWarning: Automatic importing of atari-py roms won't be supported in future releases of ale-py. Please migrate over to using `ale-import-roms` OR an ALE-supported ROM package. To make this warning disappear you can run `ale-import-roms --import-from-pkg atari_py.atari_roms`.For more information see: https://github.com/mgbellemare/Arcade-Learning-Environment#rom-management
_RESOLVED_ROMS = _resolve_roms()
[2022-05-03 16:10:40,853] Unparsed argument is detected:
['--demo_path', 'demos/table_lack/Sawyer']
/usr/local/lib/python3.8/dist-packages/ale_py/roms/__init__.py:94: DeprecationWarning: Automatic importing of atari-py roms won't be supported in future releases of ale-py. Please migrate over to using `ale-import-roms` OR an ALE-supported ROM package. To make this warning disappear you can run `ale-import-roms --import-from-pkg atari_py.atari_roms`.For more information see: https://github.com/mgbellemare/Arcade-Learning-Environment#rom-management
_RESOLVED_ROMS = _resolve_roms()
[2022-05-03 16:10:40,858] Unparsed argument is detected:
['--demo_path', 'demos/table_lack/Sawyer']
pybullet build time: Feb 28 2022 22:32:49
/usr/local/lib/python3.8/dist-packages/ale_py/roms/__init__.py:94: DeprecationWarning: Automatic importing of atari-py roms won't be supported in future releases of ale-py. Please migrate over to using `ale-import-roms` OR an ALE-supported ROM package. To make this warning disappear you can run `ale-import-roms --import-from-pkg atari_py.atari_roms`.For more information see: https://github.com/mgbellemare/Arcade-Learning-Environment#rom-management
_RESOLVED_ROMS = _resolve_roms()
[2022-05-03 16:10:41,159] Unparsed argument is detected:
['--demo_path', 'demos/table_lack/Sawyer']
pybullet build time: Feb 28 2022 22:32:49
/usr/local/lib/python3.8/dist-packages/ale_py/roms/__init__.py:94: DeprecationWarning: Automatic importing of atari-py roms won't be supported in future releases of ale-py. Please migrate over to using `ale-import-roms` OR an ALE-supported ROM package. To make this warning disappear you can run `ale-import-roms --import-from-pkg atari_py.atari_roms`.For more information see: https://github.com/mgbellemare/Arcade-Learning-Environment#rom-management
_RESOLVED_ROMS = _resolve_roms()
[2022-05-03 16:10:41,383] Unparsed argument is detected:
['--demo_path', 'demos/table_lack/Sawyer']
did i do something wrong?
I think you are running PPO
and it does not require demonstrations. Thus, you need to remove --demo_path
. Sorry for the confusion. I updated README accordingly.
Thank you for your quick reply !
So I ran it without --demo_path
like this:
mpirun -np 4 python3 -m run --algo ppo --furniture_name table_lack_0825 --num_connects 4 --max_episode_steps 800 --max_global_step 200000000 --run_prefix ppo
Getting another error, did I miss anything? I think it might be a gym version problem maybe? what version are you using? Error log:
Invalid MIT-MAGIC-COOKIE-1 keypybullet build time: Feb 28 2022 22:32:49
/usr/local/lib/python3.8/dist-packages/ale_py/roms/__init__.py:94: DeprecationWarning: Automatic importing of atari-py roms won't be supported in future releases of ale-py. Please migrate over to using `ale-import-roms` OR an ALE-supported ROM package. To make this warning disappear you can run `ale-import-roms --import-from-pkg atari_py.atari_roms`.For more information see: https://github.com/mgbellemare/Arcade-Learning-Environment#rom-management
_RESOLVED_ROMS = _resolve_roms()
[2022-05-03 19:44:40,564] Run a base worker.
[2022-05-03 19:44:40,565] Create log directory: log/table_lack_0825.ppo.ppo.123
[2022-05-03 19:44:40,565] Create video directory: log/table_lack_0825.ppo.ppo.123/video
[2022-05-03 19:44:40,565] Create demo directory: log/table_lack_0825.ppo.ppo.123/demo
[2022-05-03 19:44:40,747] Store parameters in log/table_lack_0825.ppo.ppo.123/params.json
pybullet build time: Feb 28 2022 22:32:49
/usr/local/lib/python3.8/dist-packages/ale_py/roms/__init__.py:94: DeprecationWarning: Automatic importing of atari-py roms won't be supported in future releases of ale-py. Please migrate over to using `ale-import-roms` OR an ALE-supported ROM package. To make this warning disappear you can run `ale-import-roms --import-from-pkg atari_py.atari_roms`.For more information see: https://github.com/mgbellemare/Arcade-Learning-Environment#rom-management
_RESOLVED_ROMS = _resolve_roms()
[2022-05-03 19:44:40,840] Run worker 3 and disable logger.
pybullet build time: Feb 28 2022 22:32:49
/usr/local/lib/python3.8/dist-packages/ale_py/roms/__init__.py:94: DeprecationWarning: Automatic importing of atari-py roms won't be supported in future releases of ale-py. Please migrate over to using `ale-import-roms` OR an ALE-supported ROM package. To make this warning disappear you can run `ale-import-roms --import-from-pkg atari_py.atari_roms`.For more information see: https://github.com/mgbellemare/Arcade-Learning-Environment#rom-management
_RESOLVED_ROMS = _resolve_roms()
[2022-05-03 19:44:40,997] Run worker 1 and disable logger.
pybullet build time: Feb 28 2022 22:32:49
/usr/local/lib/python3.8/dist-packages/ale_py/roms/__init__.py:94: DeprecationWarning: Automatic importing of atari-py roms won't be supported in future releases of ale-py. Please migrate over to using `ale-import-roms` OR an ALE-supported ROM package. To make this warning disappear you can run `ale-import-roms --import-from-pkg atari_py.atari_roms`.For more information see: https://github.com/mgbellemare/Arcade-Learning-Environment#rom-management
_RESOLVED_ROMS = _resolve_roms()
[2022-05-03 19:44:41,214] Run worker 2 and disable logger.
Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/tpemist/skill-chaining/run.py", line 43, in <module>
SkillChainingRun(parser).run()
File "/home/tpemist/skill-chaining/method/robot_learning/main.py", line 140, in run
trainer = self._get_trainer()
File "/home/tpemist/skill-chaining/run.py", line 26, in _get_trainer
return super()._get_trainer()
File "/home/tpemist/skill-chaining/method/robot_learning/main.py", line 136, in _get_trainer
return Trainer(self._config)
File "/home/tpemist/skill-chaining/method/robot_learning/trainer.py", line 41, in __init__
self._env = make_env(config.env, config)
File "/home/tpemist/skill-chaining/method/robot_learning/environments/__init__.py", line 24, in make_env
return get_gym_env(name, config)
File "/home/tpemist/skill-chaining/method/robot_learning/environments/__init__.py", line 52, in get_gym_env
env = GymWrapper(
File "/home/tpemist/skill-chaining/method/robot_learning/utils/gym_env.py", line 97, in __init__
max_episode_steps = self.env.spec.kwargs["max_episode_steps"]
AttributeError: 'EnvSpec' object has no attribute 'kwargs'
Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/tpemist/skill-chaining/run.py", line 43, in <module>
SkillChainingRun(parser).run()
File "/home/tpemist/skill-chaining/method/robot_learning/main.py", line 140, in run
trainer = self._get_trainer()
File "/home/tpemist/skill-chaining/run.py", line 26, in _get_trainer
return super()._get_trainer()
File "/home/tpemist/skill-chaining/method/robot_learning/main.py", line 136, in _get_trainer
return Trainer(self._config)
File "/home/tpemist/skill-chaining/method/robot_learning/trainer.py", line 41, in __init__
self._env = make_env(config.env, config)
File "/home/tpemist/skill-chaining/method/robot_learning/environments/__init__.py", line 24, in make_env
return get_gym_env(name, config)
File "/home/tpemist/skill-chaining/method/robot_learning/environments/__init__.py", line 52, in get_gym_env
env = GymWrapper(
File "/home/tpemist/skill-chaining/method/robot_learning/utils/gym_env.py", line 97, in __init__
max_episode_steps = self.env.spec.kwargs["max_episode_steps"]
AttributeError: 'EnvSpec' object has no attribute 'kwargs'
Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/tpemist/skill-chaining/run.py", line 43, in <module>
SkillChainingRun(parser).run()
File "/home/tpemist/skill-chaining/method/robot_learning/main.py", line 140, in run
trainer = self._get_trainer()
File "/home/tpemist/skill-chaining/run.py", line 26, in _get_trainer
return super()._get_trainer()
File "/home/tpemist/skill-chaining/method/robot_learning/main.py", line 136, in _get_trainer
return Trainer(self._config)
File "/home/tpemist/skill-chaining/method/robot_learning/trainer.py", line 41, in __init__
self._env = make_env(config.env, config)
File "/home/tpemist/skill-chaining/method/robot_learning/environments/__init__.py", line 24, in make_env
return get_gym_env(name, config)
File "/home/tpemist/skill-chaining/method/robot_learning/environments/__init__.py", line 52, in get_gym_env
env = GymWrapper(
File "/home/tpemist/skill-chaining/method/robot_learning/utils/gym_env.py", line 97, in __init__
max_episode_steps = self.env.spec.kwargs["max_episode_steps"]
AttributeError: 'EnvSpec' object has no attribute 'kwargs'
Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/tpemist/skill-chaining/run.py", line 43, in <module>
SkillChainingRun(parser).run()
File "/home/tpemist/skill-chaining/method/robot_learning/main.py", line 140, in run
trainer = self._get_trainer()
File "/home/tpemist/skill-chaining/run.py", line 26, in _get_trainer
return super()._get_trainer()
File "/home/tpemist/skill-chaining/method/robot_learning/main.py", line 136, in _get_trainer
return Trainer(self._config)
File "/home/tpemist/skill-chaining/method/robot_learning/trainer.py", line 41, in __init__
self._env = make_env(config.env, config)
File "/home/tpemist/skill-chaining/method/robot_learning/environments/__init__.py", line 24, in make_env
return get_gym_env(name, config)
File "/home/tpemist/skill-chaining/method/robot_learning/environments/__init__.py", line 52, in get_gym_env
env = GymWrapper(
File "/home/tpemist/skill-chaining/method/robot_learning/utils/gym_env.py", line 97, in __init__
max_episode_steps = self.env.spec.kwargs["max_episode_steps"]
AttributeError: 'EnvSpec' object has no attribute 'kwargs'
--------------------------------------------------------------------------
Primary job terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:
Process name: [[35163,1],3]
Exit code: 1
error log:
I first ran the command:
# Sub-task demo generation
and got the folder demos/table_lack with lots of Sawyer_table_lack_0825_xxx.pkl files
then run the command:
and I ran into the error metioned above, what's the demo_path trying to get? did I miss anything? or I'm running to other problem? Thanks