Search Unity

  1. We are migrating the Unity Forums to Unity Discussions. On July 12, the Unity Forums will become read-only. On July 15, Unity Discussions will become read-only until July 18, when the new design and the migrated forum contents will go live. Read our full announcement for more information and let us know if you have any questions.

Error when training ML-agents Penguin Tutorial: Environment stopping

Discussion in 'ML-Agents' started by mqc410872027, Apr 10, 2020.

  1. mqc410872027

    mqc410872027

    Joined:
    Apr 6, 2020
    Posts:
    1
    Hi
    I am very new to this and just started to follow the ml-agents: penguins.
    After I started training (by entering the command in Anaconda Prompt) and pressed the playing button in the Unity Editor, it gives me below error:

    (ml-agents) PS C:\Users\41087> cd "G:\Project Genesis\ml-agents-master\ml-agents-0.13.1\ml-agents-0.13.1"
    (ml-agents) PS G:\Project Genesis\ml-agents-master\ml-agents-0.13.1\ml-agents-0.13.1> mlagents-learn config/trainer_config.yaml --curriculum config/curricula/penguin --run-id penguin_01 --train
    WARNING:tensorflow:From C:\Users\41087\Anaconda3\envs\ml-agents\lib\site-packages\tensorflow_core\python\compat\v2_compat.py:65: disable_resource_variables (from tensorflow.python.ops.variable_scope) is deprecated and will be removed in a future version.
    Instructions for updating:
    non-resource variables are not supported in the long term


    ▄▄▄▓▓▓▓
    ╓▓▓▓▓▓▓█▓▓▓▓▓
    ,▄▄▄m▀▀▀' ,▓▓▓▀▓▓▄ ▓▓▓ ▓▓▌
    ▄▓▓▓▀' ▄▓▓▀ ▓▓▓ ▄▄ ▄▄ ,▄▄ ▄▄▄▄ ,▄▄ ▄▓▓▌▄ ▄▄▄ ,▄▄
    ▄▓▓▓▀ ▄▓▓▀ ▐▓▓▌ ▓▓▌ ▐▓▓ ▐▓▓▓▀▀▀▓▓▌ ▓▓▓ ▀▓▓▌▀ ^▓▓▌ ╒▓▓▌
    ▄▓▓▓▓▓▄▄▄▄▄▄▄▄▓▓▓ ▓▀ ▓▓▌ ▐▓▓ ▐▓▓ ▓▓▓ ▓▓▓ ▓▓▌ ▐▓▓▄ ▓▓▌
    ▀▓▓▓▓▀▀▀▀▀▀▀▀▀▀▓▓▄ ▓▓ ▓▓▌ ▐▓▓ ▐▓▓ ▓▓▓ ▓▓▓ ▓▓▌ ▐▓▓▐▓▓
    ^█▓▓▓ ▀▓▓▄ ▐▓▓▌ ▓▓▓▓▄▓▓▓▓ ▐▓▓ ▓▓▓ ▓▓▓ ▓▓▓▄ ▓▓▓▓`
    '▀▓▓▓▄ ^▓▓▓ ▓▓▓ └▀▀▀▀ ▀▀ ^▀▀ `▀▀ `▀▀ '▀▀ ▐▓▓▌
    ▀▀▀▀▓▄▄▄ ▓▓▓▓▓▓, ▓▓▓▓▀
    `▀█▓▓▓▓▓▓▓▓▓▌
    ¬`▀▀▀█▓


    Version information:
    ml-agents: 0.13.1,
    ml-agents-envs: 0.13.1,
    Communicator API: API-13,
    TensorFlow: 2.0.1
    INFO:mlagents.trainers:CommandLineOptions(debug=False, num_runs=1, seed=-1, env_path=None, run_id='penguin_01', load_model=False, train_model=True, save_freq=50000, keep_checkpoints=5, base_port=5005, num_envs=1, curriculum_folder='config/curricula/penguin', lesson=0, no_graphics=False, multi_gpu=False, trainer_config_path='config/trainer_config.yaml', sampler_file_path=None, docker_target_name=None, env_args=None, cpu=False, width=84, height=84, quality_level=5, time_scale=20, target_frame_rate=-1)
    INFO:mlagents_envs:Listening on port 5004. Start training by pressing the Play button in the Unity Editor.
    INFO:mlagents.trainers:UnityEnvironment worker 0: environment stopping due to UnityTimeOutException
    INFO:mlagents.trainers:Learning was interrupted. Please wait while the graph is generated.
    INFO:mlagents.trainers:Saved Model
    (ml-agents) PS G:\Project Genesis\ml-agents-master\ml-agents-0.13.1\ml-agents-0.13.1>




    ====================================

    Further investigation determined it is due to UnityTimeOutException error. Could anyone help, much appreciated!!

    Ml-agent version 0.13.1
    Unity 2019.3.8f1
    Barracuda ver 0.4.0
     

    Attached Files:

    • 1.PNG
      1.PNG
      File size:
      68.3 KB
      Views:
      354
  2. TreyK-47

    TreyK-47

    Unity Technologies

    Joined:
    Oct 22, 2019
    Posts:
    1,843
    I'll forward this to the team so they can take a look.
     
  3. WalkLearner

    WalkLearner

    Joined:
    Mar 12, 2020
    Posts:
    10
    If you follow the latest penguin example from this link, you should have the exact version of the environment that the demonstrator has, i.e. ML-agents 0.14.0 and Unity 2018.4.14f1.
     
  4. christophergoy

    christophergoy

    Unity Technologies

    Joined:
    Sep 16, 2015
    Posts:
    735
    could you print out the debug console from unity as well? I'm not sure what the issue is exactly.
     
  5. christophergoy

    christophergoy

    Unity Technologies

    Joined:
    Sep 16, 2015
    Posts:
    735
    It looks like the port is wrong in the connection. It should be on port 5004, not 5005.
     
  6. christophergoy

    christophergoy

    Unity Technologies

    Joined:
    Sep 16, 2015
    Posts:
    735
    you can add the --base_port=5004 option when you run the command and it should work