Question Unable to train with linux executable

Hello,

I was trying to train an ML-Agents project using linux executable, but it reported error. The complete log was shown as following:

~/ml-agents-release_20/unity-volume$ mlagents-learn 3DBall.yaml --env=3DBall.x86_64 --run-id=test --no-graphics --train

┐ ╖
╓╖╬│╡ ││╬╖╖
╓╖╬│││││┘ ╬│││││╬╖
╖╬│││││╬╜ ╙╬│││││╖╖ ╗╗╗
╬╬╬╬╖││╦╖ ╖╬││╗╣╣╣╬ ╟╣╣╬ ╟╣╣╣ ╜╜╜ ╟╣╣
╬╬╬╬╬╬╬╬╖│╬╖╖╓╬╪│╓╣╣╣╣╣╣╣╬ ╟╣╣╬ ╟╣╣╣ ╒╣╣╖╗╣╣╣╗ ╣╣╣ ╣╣╣╣╣╣ ╟╣╣╖ ╣╣╣
╬╬╬╬┐ ╙╬╬╬╬│╓╣╣╣╝╜ ╫╣╣╣╬ ╟╣╣╬ ╟╣╣╣ ╟╣╣╣╙ ╙╣╣╣ ╣╣╣ ╙╟╣╣╜╙ ╫╣╣ ╟╣╣
╬╬╬╬┐ ╙╬╬╣╣ ╫╣╣╣╬ ╟╣╣╬ ╟╣╣╣ ╟╣╣╬ ╣╣╣ ╣╣╣ ╟╣╣ ╣╣╣┌╣╣╜
╬╬╬╜ ╬╬╣╣ ╙╝╣╣╬ ╙╣╣╣╗╖╓╗╣╣╣╜ ╟╣╣╬ ╣╣╣ ╣╣╣ ╟╣╣╦╓ ╣╣╣╣╣
╙ ╓╦╖ ╬╬╣╣ ╓╗╗╖ ╙╝╣╣╣╣╝╜ ╘╝╝╜ ╝╝╝ ╝╝╝ ╙╣╣╣ ╟╣╣╣
╩╬╬╬╬╬╬╦╦╬╬╣╣╗╣╣╣╣╣╣╣╝ ╫╣╣╣╣
╙╬╬╬╬╬╬╬╣╣╣╣╣╣╝╜
╙╬╬╬╣╣╣╜
╙

Version information:
ml-agents: 0.30.0,
ml-agents-envs: 0.30.0,
Communicator API: 1.5.0,
PyTorch: 1.11.0+cu102
[WARNING] The --train option has been deprecated. Train mode is now the default. Use --inference to run in inference mode.
[INFO] Learning was interrupted. Please wait while the graph is generated.
Traceback (most recent call last):
File "/home/lya/.local/bin/mlagents-learn", line 8, in <module>
sys.exit(main())
File "/home/lya/.local/lib/python3.10/site-packages/mlagents/trainers/learn.py", line 264, in main
run_cli(parse_command_line())
File "/home/lya/.local/lib/python3.10/site-packages/mlagents/trainers/learn.py", line 260, in run_cli
run_training(run_seed, options, num_areas)
File "/home/lya/.local/lib/python3.10/site-packages/mlagents/trainers/learn.py", line 136, in run_training
tc.start_learning(env_manager)
File "/home/lya/.local/lib/python3.10/site-packages/mlagents_envs/timers.py", line 305, in wrapped
return func(*args, **kwargs)
File "/home/lya/.local/lib/python3.10/site-packages/mlagents/trainers/trainer_controller.py", line 197, in start_learning
raise ex
File "/home/lya/.local/lib/python3.10/site-packages/mlagents/trainers/trainer_controller.py", line 172, in start_learning
self._reset_env(env_manager)
File "/home/lya/.local/lib/python3.10/site-packages/mlagents_envs/timers.py", line 305, in wrapped
return func(*args, **kwargs)
File "/home/lya/.local/lib/python3.10/site-packages/mlagents/trainers/trainer_controller.py", line 105, in _reset_env
env_manager.reset(config=new_config)
File "/home/lya/.local/lib/python3.10/site-packages/mlagents/trainers/env_manager.py", line 68, in reset
self.first_step_infos = self._reset_env(config)
File "/home/lya/.local/lib/python3.10/site-packages/mlagents/trainers/subprocess_env_manager.py", line 446, in _reset_env
ew.previous_step = EnvironmentStep(ew.recv().payload, ew.worker_id, {}, {})
File "/home/lya/.local/lib/python3.10/site-packages/mlagents/trainers/subprocess_env_manager.py", line 101, in recv
raise env_exception
mlagents_envs.exception.UnityEnvironmentException: Environment shut down with return code 127.


I also tried to use learn.py but also got error above, and I couldn't figure out why. I would appreciate it a lot if anyone could help. Thanks!

 

i have the same problem, could you solve it?

 

Does your Agent have the component "Decision Requester"? I was receiving these error messages and adding that component fixed the issue.