Polu's picture
First Push
87ee535 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9147663116455078,
"min": 0.9147663116455078,
"max": 2.8700132369995117,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8734.1884765625,
"min": 8734.1884765625,
"max": 29391.806640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.845898628234863,
"min": 0.385421484708786,
"max": 12.845898628234863,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.9501953125,
"min": 74.77176666259766,
"max": 2610.3583984375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06883408878895673,
"min": 0.06196707829056358,
"max": 0.07517206691352162,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27533635515582694,
"min": 0.2516331164321552,
"max": 0.3640947190419242,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2122234125055519,
"min": 0.13668477693663947,
"max": 0.3015543877494101,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8488936500222076,
"min": 0.5467391077465579,
"max": 1.5077719387470505,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.545454545454547,
"min": 3.6363636363636362,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 160.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.6363636363636362,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 160.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1705093024",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1705093508"
},
"total": 484.5108390280002,
"count": 1,
"self": 0.48603473000048325,
"children": {
"run_training.setup": {
"total": 0.050355804999981046,
"count": 1,
"self": 0.050355804999981046
},
"TrainerController.start_learning": {
"total": 483.9744484929997,
"count": 1,
"self": 0.6444142449890933,
"children": {
"TrainerController._reset_env": {
"total": 1.8720092399998975,
"count": 1,
"self": 1.8720092399998975
},
"TrainerController.advance": {
"total": 481.36539432001064,
"count": 18200,
"self": 0.32646810399546666,
"children": {
"env_step": {
"total": 481.03892621601517,
"count": 18200,
"self": 317.99321693599404,
"children": {
"SubprocessEnvManager._take_step": {
"total": 162.73155287003692,
"count": 18200,
"self": 1.5944427020076546,
"children": {
"TorchPolicy.evaluate": {
"total": 161.13711016802927,
"count": 18200,
"self": 161.13711016802927
}
}
},
"workers": {
"total": 0.31415640998420713,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 482.64776126700554,
"count": 18200,
"is_parallel": true,
"self": 235.99564909299897,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002004618999762897,
"count": 1,
"is_parallel": true,
"self": 0.0005810749989905162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001423544000772381,
"count": 10,
"is_parallel": true,
"self": 0.001423544000772381
}
}
},
"UnityEnvironment.step": {
"total": 0.04470639100009066,
"count": 1,
"is_parallel": true,
"self": 0.0007961699998304539,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004575070001919812,
"count": 1,
"is_parallel": true,
"self": 0.0004575070001919812
},
"communicator.exchange": {
"total": 0.04119802199966216,
"count": 1,
"is_parallel": true,
"self": 0.04119802199966216
},
"steps_from_proto": {
"total": 0.0022546920004060667,
"count": 1,
"is_parallel": true,
"self": 0.00045567699999082834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017990150004152383,
"count": 10,
"is_parallel": true,
"self": 0.0017990150004152383
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 246.65211217400656,
"count": 18199,
"is_parallel": true,
"self": 11.370700237991969,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.830309776987633,
"count": 18199,
"is_parallel": true,
"self": 5.830309776987633
},
"communicator.exchange": {
"total": 192.26405026900147,
"count": 18199,
"is_parallel": true,
"self": 192.26405026900147
},
"steps_from_proto": {
"total": 37.18705189002549,
"count": 18199,
"is_parallel": true,
"self": 6.947141849037507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.23991004098798,
"count": 181990,
"is_parallel": true,
"self": 30.23991004098798
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.852600002574036e-05,
"count": 1,
"self": 3.852600002574036e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 475.14516910872226,
"count": 720812,
"is_parallel": true,
"self": 15.49547574575854,
"children": {
"process_trajectory": {
"total": 262.6520678459606,
"count": 720812,
"is_parallel": true,
"self": 261.4102950779602,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2417727680003736,
"count": 4,
"is_parallel": true,
"self": 1.2417727680003736
}
}
},
"_update_policy": {
"total": 196.99762551700314,
"count": 90,
"is_parallel": true,
"self": 63.6688552550022,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.32877026200094,
"count": 4587,
"is_parallel": true,
"self": 133.32877026200094
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09259216200007359,
"count": 1,
"self": 0.001341058000434714,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09125110399963887,
"count": 1,
"self": 0.09125110399963887
}
}
}
}
}
}
}