-
-
Save carefish/3e5193f94103c14707e925c3bf65977f to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // Other version info: | |
| Unity 2020.3.10f1 | |
| ml agents 2.0.0-exp.1 | |
| //=== | |
| Version information: | |
| ml-agents: 0.26.0, | |
| ml-agents-envs: 0.26.0, | |
| Communicator API: 1.5.0, | |
| PyTorch: 1.7.1+cu110 | |
| [INFO] Listening on port 5004. Start training by pressing the Play button in the Unity Editor. | |
| [INFO] Connected to Unity environment with package version 2.0.0-exp.1 and communication version 1.5.0 | |
| [INFO] Connected new brain: Behaviour_Arena0?team=0 | |
| 2021-06-04 11:03:16.890577: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library cudart64_110.dll | |
| [INFO] Hyperparameters for behavior name Behaviour_Arena0: | |
| trainer_type: ppo | |
| hyperparameters: | |
| batch_size: 128 | |
| buffer_size: 2048 | |
| learning_rate: 0.0003 | |
| learning_rate_schedule: linear | |
| network_settings: | |
| normalize: False | |
| hidden_units: 256 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| memory: None | |
| goal_conditioning_type: hyper | |
| reward_signals: | |
| extrinsic: | |
| gamma: 0.99 | |
| strength: 1.0 | |
| network_settings: | |
| normalize: False | |
| hidden_units: 128 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| memory: None | |
| goal_conditioning_type: hyper | |
| gail: | |
| gamma: 0.99 | |
| strength: 0.25 | |
| network_settings: | |
| normalize: False | |
| hidden_units: 128 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| memory: None | |
| goal_conditioning_type: hyper | |
| init_path: None | |
| keep_checkpoints: 5 | |
| checkpoint_interval: 500000 | |
| max_steps: 2500000 | |
| time_horizon: 64 | |
| summary_freq: 60000 | |
| threaded: False | |
| self_play: None | |
| behavioral_cloning: | |
| demo_path: ProjectFolder/Assets/Demos | |
| steps: 2500000 | |
| strength: 0.25 | |
| samples_per_update: 0 | |
| num_epoch: None | |
| batch_size: None | |
| [WARNING] Trainer has no policies, not saving anything. | |
| Traceback (most recent call last): | |
| File "C:\Python\Python38\lib\runpy.py", line 194, in _run_module_as_main | |
| return _run_code(code, main_globals, None, | |
| File "C:\Python\Python38\lib\runpy.py", line 87, in _run_code | |
| exec(code, run_globals) | |
| File "C:\proj\python-envs\sample-env\Scripts\mlagents-learn.exe\__main__.py", line 7, in <module> | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\learn.py", line 250, in main | |
| run_cli(parse_command_line()) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\learn.py", line 246, in run_cli | |
| run_training(run_seed, options) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\learn.py", line 125, in run_training | |
| tc.start_learning(env_manager) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents_envs\timers.py", line 305, in wrapped | |
| return func(*args, **kwargs) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\trainer_controller.py", line 173, in start_learning | |
| self._reset_env(env_manager) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents_envs\timers.py", line 305, in wrapped | |
| return func(*args, **kwargs) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\trainer_controller.py", line 107, in _reset_env | |
| self._register_new_behaviors(env_manager, env_manager.first_step_infos) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\trainer_controller.py", line 268, in _register_new_behaviors | |
| self._create_trainers_and_managers(env_manager, new_behavior_ids) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\trainer_controller.py", line 166, in _create_trainers_and_managers | |
| self._create_trainer_and_manager(env_manager, behavior_id) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\trainer_controller.py", line 137, in _create_trainer_and_manager | |
| policy = trainer.create_policy( | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\trainer\rl_trainer.py", line 119, in create_policy | |
| return self.create_torch_policy(parsed_behavior_id, behavior_spec) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\ppo\trainer.py", line 226, in create_torch_policy | |
| policy = TorchPolicy( | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\policy\torch_policy.py", line 65, in __init__ | |
| self.actor = SimpleActor( | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\torch\networks.py", line 592, in __init__ | |
| self.network_body = NetworkBody(observation_specs, network_settings) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\torch\networks.py", line 212, in __init__ | |
| self._body_endoder = LinearEncoder( | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\torch\layers.py", line 148, in __init__ | |
| linear_layer( | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\mlagents\trainers\torch\layers.py", line 49, in linear_layer | |
| layer = torch.nn.Linear(input_size, output_size) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\torch\nn\modules\linear.py", line 83, in __init__ | |
| self.reset_parameters() | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\torch\nn\modules\linear.py", line 86, in reset_parameters | |
| init.kaiming_uniform_(self.weight, a=math.sqrt(5)) | |
| File "c:\proj\python-envs\sample-env\lib\site-packages\torch\nn\init.py", line 381, in kaiming_uniform_ | |
| std = gain / math.sqrt(fan) | |
| ZeroDivisionError: float division by zero |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| behaviors: | |
| Behaviour_Arena0: | |
| trainer_type: ppo | |
| hyperparameters: | |
| batch_size: 128 | |
| buffer_size: 2048 | |
| 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: 256 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| reward_signals: | |
| extrinsic: | |
| gamma: 0.99 | |
| strength: 1.0 | |
| gail: | |
| gamma: 0.99 | |
| strength: 0.25 | |
| network_settings: | |
| normalize: false | |
| hidden_units: 128 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| learning_rate: 0.0003 | |
| use_actions: false | |
| use_vail: false | |
| demo_path: ProjectFolder/Assets/Demos | |
| keep_checkpoints: 5 | |
| max_steps: 2500000 | |
| time_horizon: 64 | |
| summary_freq: 60000 | |
| behavioral_cloning: | |
| demo_path: ProjectFolder/Assets/Demos | |
| steps: 2500000 | |
| strength: 0.25 | |
| samples_per_update: 0 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment