Actuary's picture
First Push
4097018
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8965212106704712,
"min": 0.8965212106704712,
"max": 2.8476932048797607,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8599.431640625,
"min": 8599.431640625,
"max": 29225.875,
"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": 13.056207656860352,
"min": 0.42233338952064514,
"max": 13.056207656860352,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2545.96044921875,
"min": 81.93267822265625,
"max": 2645.7431640625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06428697935609984,
"min": 0.06219308111547291,
"max": 0.07283064166891992,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25714791742439935,
"min": 0.253794996680774,
"max": 0.36415320834459963,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2016227744227531,
"min": 0.12117704873055439,
"max": 0.2690818102920757,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8064910976910123,
"min": 0.48470819492221756,
"max": 1.3454090514603783,
"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": 25.727272727272727,
"min": 3.6136363636363638,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 159.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 3.6136363636363638,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 159.0,
"max": 1412.0,
"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": "1683736707",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683737094"
},
"total": 386.96057435299997,
"count": 1,
"self": 0.2759785100000727,
"children": {
"run_training.setup": {
"total": 0.05108021999990342,
"count": 1,
"self": 0.05108021999990342
},
"TrainerController.start_learning": {
"total": 386.633515623,
"count": 1,
"self": 0.5664840070039645,
"children": {
"TrainerController._reset_env": {
"total": 3.9870886520000113,
"count": 1,
"self": 3.9870886520000113
},
"TrainerController.advance": {
"total": 381.9465025749962,
"count": 18206,
"self": 0.2514111849936853,
"children": {
"env_step": {
"total": 381.6950913900025,
"count": 18206,
"self": 274.02313459801167,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.42731698699731,
"count": 18206,
"self": 1.4536046400044143,
"children": {
"TorchPolicy.evaluate": {
"total": 105.9737123469929,
"count": 18206,
"self": 105.9737123469929
}
}
},
"workers": {
"total": 0.24463980499353966,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 385.77453873600143,
"count": 18206,
"is_parallel": true,
"self": 191.51265106801736,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021259689999624243,
"count": 1,
"is_parallel": true,
"self": 0.0007368509998286754,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013891180001337489,
"count": 10,
"is_parallel": true,
"self": 0.0013891180001337489
}
}
},
"UnityEnvironment.step": {
"total": 0.03470568800003093,
"count": 1,
"is_parallel": true,
"self": 0.0005321800000501753,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002825029999939943,
"count": 1,
"is_parallel": true,
"self": 0.0002825029999939943
},
"communicator.exchange": {
"total": 0.03205879500001174,
"count": 1,
"is_parallel": true,
"self": 0.03205879500001174
},
"steps_from_proto": {
"total": 0.0018322099999750208,
"count": 1,
"is_parallel": true,
"self": 0.0003201850000777995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015120249998972213,
"count": 10,
"is_parallel": true,
"self": 0.0015120249998972213
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 194.26188766798407,
"count": 18205,
"is_parallel": true,
"self": 9.018999922975695,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.745022356002096,
"count": 18205,
"is_parallel": true,
"self": 4.745022356002096
},
"communicator.exchange": {
"total": 151.68447986701074,
"count": 18205,
"is_parallel": true,
"self": 151.68447986701074
},
"steps_from_proto": {
"total": 28.813385521995542,
"count": 18205,
"is_parallel": true,
"self": 5.225260672029208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.588124849966334,
"count": 182050,
"is_parallel": true,
"self": 23.588124849966334
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014355099983731634,
"count": 1,
"self": 0.00014355099983731634,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 380.5500214819773,
"count": 236739,
"is_parallel": true,
"self": 4.794163842028638,
"children": {
"process_trajectory": {
"total": 210.62826672294773,
"count": 236739,
"is_parallel": true,
"self": 209.7859311519478,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8423355709999214,
"count": 4,
"is_parallel": true,
"self": 0.8423355709999214
}
}
},
"_update_policy": {
"total": 165.12759091700093,
"count": 90,
"is_parallel": true,
"self": 43.92360788700239,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.20398302999854,
"count": 4587,
"is_parallel": true,
"self": 121.20398302999854
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13329683799997838,
"count": 1,
"self": 0.0008723779999399994,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13242446000003838,
"count": 1,
"self": 0.13242446000003838
}
}
}
}
}
}
}