n1kolAI's picture
First Push
c60e30a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9977692365646362,
"min": 0.9977692365646362,
"max": 2.869685411453247,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9548.6513671875,
"min": 9548.6513671875,
"max": 29420.015625,
"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": 12.535900115966797,
"min": 0.2981874346733093,
"max": 12.535900115966797,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2444.50048828125,
"min": 57.84836196899414,
"max": 2508.849609375,
"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": 0.06605846012134148,
"min": 0.06459182519602688,
"max": 0.07470293323881468,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2642338404853659,
"min": 0.2583673007841075,
"max": 0.37351466619407336,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19231485093341155,
"min": 0.1071793062957095,
"max": 0.2680786159108667,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7692594037336462,
"min": 0.428717225182838,
"max": 1.3403930795543335,
"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": 25.318181818181817,
"min": 3.2045454545454546,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 141.0,
"max": 1369.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.2045454545454546,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 141.0,
"max": 1369.0,
"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": "1710498960",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710499565"
},
"total": 605.2175849060004,
"count": 1,
"self": 0.5389811030017881,
"children": {
"run_training.setup": {
"total": 0.07753361999857589,
"count": 1,
"self": 0.07753361999857589
},
"TrainerController.start_learning": {
"total": 604.601070183,
"count": 1,
"self": 0.8611122150050505,
"children": {
"TrainerController._reset_env": {
"total": 3.716398818000016,
"count": 1,
"self": 3.716398818000016
},
"TrainerController.advance": {
"total": 599.9234812049945,
"count": 18201,
"self": 0.44542303092930524,
"children": {
"env_step": {
"total": 599.4780581740652,
"count": 18201,
"self": 458.2535086773132,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.79835725485464,
"count": 18201,
"self": 2.7447104548664356,
"children": {
"TorchPolicy.evaluate": {
"total": 138.0536467999882,
"count": 18201,
"self": 138.0536467999882
}
}
},
"workers": {
"total": 0.4261922418972972,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 602.6817798250158,
"count": 18201,
"is_parallel": true,
"self": 279.4560887840762,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007459047999873292,
"count": 1,
"is_parallel": true,
"self": 0.004672430000937311,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027866179989359807,
"count": 10,
"is_parallel": true,
"self": 0.0027866179989359807
}
}
},
"UnityEnvironment.step": {
"total": 0.048609229999783565,
"count": 1,
"is_parallel": true,
"self": 0.0008869800003594719,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005854800001543481,
"count": 1,
"is_parallel": true,
"self": 0.0005854800001543481
},
"communicator.exchange": {
"total": 0.044643930999882286,
"count": 1,
"is_parallel": true,
"self": 0.044643930999882286
},
"steps_from_proto": {
"total": 0.002492838999387459,
"count": 1,
"is_parallel": true,
"self": 0.0004698699958680663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020229690035193926,
"count": 10,
"is_parallel": true,
"self": 0.0020229690035193926
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 323.22569104093964,
"count": 18200,
"is_parallel": true,
"self": 15.909670715605898,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.904143619156457,
"count": 18200,
"is_parallel": true,
"self": 7.904143619156457
},
"communicator.exchange": {
"total": 252.37881511300657,
"count": 18200,
"is_parallel": true,
"self": 252.37881511300657
},
"steps_from_proto": {
"total": 47.033061593170714,
"count": 18200,
"is_parallel": true,
"self": 9.433346354961031,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.59971523820968,
"count": 182000,
"is_parallel": true,
"self": 37.59971523820968
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0006451060016843257,
"count": 1,
"self": 0.0006451060016843257,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 592.2968366819841,
"count": 831264,
"is_parallel": true,
"self": 20.057298861642266,
"children": {
"process_trajectory": {
"total": 325.6391120183398,
"count": 831264,
"is_parallel": true,
"self": 324.38403946834296,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2550725499968394,
"count": 4,
"is_parallel": true,
"self": 1.2550725499968394
}
}
},
"_update_policy": {
"total": 246.60042580200206,
"count": 90,
"is_parallel": true,
"self": 65.6374239650122,
"children": {
"TorchPPOOptimizer.update": {
"total": 180.96300183698986,
"count": 4587,
"is_parallel": true,
"self": 180.96300183698986
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09943283899883681,
"count": 1,
"self": 0.0012752649981848663,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09815757400065195,
"count": 1,
"self": 0.09815757400065195
}
}
}
}
}
}
}