chriselion
commented
3 years ago Closed hyuDev closed 3 years ago
chriselion
commented
3 years ago 
hyuDev
commented
3 years ago @chriselion Hi I know already that SIGABRT (from one of your other messages) means the environment crashed. I don't know why the environment crashed, because I didn't fix anything, and all the settings are in the state where the project is saved. If my graphic setting(or setup) is a problem, where and how should I fix it? the problem happened all os( window, ubuntu, mac os) What information do you think it will be easy for me to solve this problem?
Just in case, I'm leaving behind the command and debug results.
(ml-agents) BBookPro:python B$ mlagents-learn /Users/B/Downloads/ml-agents-release_14/config/ppo/VisualPushBlock.yaml --env="vi14_0513" --run-id=push_051 --debug
▄▄▄▓▓▓▓
╓▓▓▓▓▓▓█▓▓▓▓▓
,▄▄▄m▀▀▀' ,▓▓▓▀▓▓▄ ▓▓▓ ▓▓▌
▄▓▓▓▀' ▄▓▓▀ ▓▓▓ ▄▄ ▄▄ ,▄▄ ▄▄▄▄ ,▄▄ ▄▓▓▌▄ ▄▄▄ ,▄▄
▄▓▓▓▀ ▄▓▓▀ ▐▓▓▌ ▓▓▌ ▐▓▓ ▐▓▓▓▀▀▀▓▓▌ ▓▓▓ ▀▓▓▌▀ ^▓▓▌ ╒▓▓▌
▄▓▓▓▓▓▄▄▄▄▄▄▄▄▓▓▓ ▓▀ ▓▓▌ ▐▓▓ ▐▓▓ ▓▓▓ ▓▓▓ ▓▓▌ ▐▓▓▄ ▓▓▌
▀▓▓▓▓▀▀▀▀▀▀▀▀▀▀▓▓▄ ▓▓ ▓▓▌ ▐▓▓ ▐▓▓ ▓▓▓ ▓▓▓ ▓▓▌ ▐▓▓▐▓▓
^█▓▓▓ ▀▓▓▄ ▐▓▓▌ ▓▓▓▓▄▓▓▓▓ ▐▓▓ ▓▓▓ ▓▓▓ ▓▓▓▄ ▓▓▓▓`
'▀▓▓▓▄ ^▓▓▓ ▓▓▓ └▀▀▀▀ ▀▀ ^▀▀ `▀▀ `▀▀ '▀▀ ▐▓▓▌
▀▀▀▀▓▄▄▄ ▓▓▓▓▓▓, ▓▓▓▓▀
`▀█▓▓▓▓▓▓▓▓▓▌
¬`▀▀▀█▓Version information:
ml-agents: 0.24.1,
ml-agents-envs: 0.24.1,
Communicator API: 1.4.0,
PyTorch: 1.7.1
2021-05-14 09:55:25 DEBUG [learn.py:220] Configuration for this run:
2021-05-14 09:55:25 DEBUG [learn.py:221] {
"default_settings": null,
"behaviors": {
"VisualPushBlock": {
"trainer_type": "ppo",
"hyperparameters": {
"batch_size": 64,
"buffer_size": 1024,
"learning_rate": 0.0003,
"beta": 0.01,
"epsilon": 0.2,
"lambd": 0.95,
"num_epoch": 3,
"learning_rate_schedule": "linear"
},
"network_settings": {
"normalize": false,
"hidden_units": 128,
"num_layers": 1,
"vis_encode_type": "simple",
"memory": {
"sequence_length": 32,
"memory_size": 128
}
},
"reward_signals": {
"extrinsic": {
"gamma": 0.99,
"strength": 1.0
}
},
"init_path": null,
"keep_checkpoints": 5,
"checkpoint_interval": 500000,
"max_steps": 3000000,
"time_horizon": 64,
"summary_freq": 60000,
"threaded": true,
"self_play": null,
"behavioral_cloning": null
}
},
"env_settings": {
"env_path": "vi14_0513",
"env_args": null,
"base_port": 5005,
"num_envs": 1,
"seed": -1
},
"engine_settings": {
"width": 84,
"height": 84,
"quality_level": 5,
"time_scale": 20,
"target_frame_rate": -1,
"capture_frame_rate": 60,
"no_graphics": false
},
"environment_parameters": null,
"checkpoint_settings": {
"run_id": "push_051",
"initialize_from": null,
"load_model": false,
"resume": false,
"force": true,
"train_model": false,
"inference": false,
"results_dir": "results"
},
"torch_settings": {
"device": null
},
"debug": true
}
2021-05-14 09:55:25 INFO [learn.py:245] run_seed set to 7444
2021-05-14 09:55:25 INFO [torch.py:58] default Torch device: cpu
2021-05-14 09:55:25 DEBUG [stats_writer.py:59] Initializing StatsWriter plugins: default
2021-05-14 09:55:25 DEBUG [stats_writer.py:63] Found 3 StatsWriters for plugin default
2021-05-14 09:55:25 DEBUG [env_utils.py:33] The true file name is vi14_0513
2021-05-14 09:55:25 DEBUG [env_utils.py:105] The launch string is /Users/B/Downloads/ml-agents-release_14/python/vi14_0513.app/Contents/MacOS/UnityEnvironment
2021-05-14 09:55:25 DEBUG [env_utils.py:106] Running with args ['--mlagents-port', '5005', '-logFile', '/Users/B/Downloads/ml-agents-release_14/python/results/push_051/run_logs/Player-0.log']
2021-05-14 09:55:26 INFO [environment.py:112] Connected to Unity environment with package version 1.8.1-preview and communication version 1.4.0
2021-05-14 09:55:32 INFO [subprocess_env_manager.py:220] UnityEnvironment worker 0: environment stopping.
2021-05-14 09:55:32 DEBUG [subprocess_env_manager.py:234] UnityEnvironment worker 0 closing.
2021-05-14 09:55:32 INFO [trainer_controller.py:188] Learning was interrupted. Please wait while the graph is generated.
2021-05-14 09:55:32 INFO [trainer_controller.py:81] Saved Model
2021-05-14 09:55:32 DEBUG [subprocess_env_manager.py:368] SubprocessEnvManager closing.
2021-05-14 09:55:32 INFO [environment.py:426] Environment shut down with return code -6 (SIGABRT).
2021-05-14 09:55:32 DEBUG [subprocess_env_manager.py:237] UnityEnvironment worker 0 done.
Traceback (most recent call last):
File "/Users/B/opt/anaconda3/envs/ml-agents/bin/mlagents-learn", line 33, in
chriselion
commented
3 years ago You'll need to look in the player logs for more details; generally there will be a stack trace. This line tells you where they are saved:
2021-05-14 09:55:25 DEBUG [env_utils.py:106] Running with args ['--mlagents-port', '5005', '-logFile', '/Users/B/Downloads/ml-agents-release_14/python/results/push_051/run_logs/Player-0.log']
stale[bot]
commented
3 years ago This issue has been automatically marked as stale because it has not had activity in the last 14 days. It will be closed in the next 14 days if no further activity occurs. Thank you for your contributions.
stale[bot]
commented
3 years ago This issue has been automatically closed because it has not had activity in the last 28 days. If this issue is still valid, please ping a maintainer. Thank you for your contributions.
github-actions[bot]
commented
3 years ago This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.
hi I train the model with example code. Until yesterday, mlagents-learn worked well, but suddenly it didn't work with this error code.
File "c:\dev\ml-agents-release_14\ml-agents\mlagents\trainers\subprocess_env_manager.py", line 98, in recv raise env_exception mlagents_envs.exception.UnityEnvironmentException: Environment shut down with return code xxx.
I haven't updated anything, and nothing has changed, what's wrong with you? The returned code is 0 or 3221225477.