-N
Huggy
fd0082e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4058910608291626,
"min": 1.4058910608291626,
"max": 1.425048589706421,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71270.2421875,
"min": 68507.5625,
"max": 78717.4296875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.3382084095064,
"min": 80.61337683523654,
"max": 400.92,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49415.0,
"min": 48940.0,
"max": 50115.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999900.0,
"min": 49757.0,
"max": 1999900.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999900.0,
"min": 49757.0,
"max": 1999900.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3710386753082275,
"min": 0.05547558516263962,
"max": 2.443535566329956,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1299.3292236328125,
"min": 6.87897253036499,
"max": 1456.3857421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.60566076745082,
"min": 1.8060445376942236,
"max": 3.9561117785762114,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1975.9021005630493,
"min": 223.9495226740837,
"max": 2322.562780082226,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.60566076745082,
"min": 1.8060445376942236,
"max": 3.9561117785762114,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1975.9021005630493,
"min": 223.9495226740837,
"max": 2322.562780082226,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015266245614879556,
"min": 0.014478479826721014,
"max": 0.020085772580569025,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04579873684463867,
"min": 0.028956959653442027,
"max": 0.056153008759914275,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056776321596569486,
"min": 0.021236871741712092,
"max": 0.05897581573161814,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17032896478970846,
"min": 0.042473743483424184,
"max": 0.17692744719485443,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.43214885598333e-06,
"min": 3.43214885598333e-06,
"max": 0.0002953030515656499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.029644656794999e-05,
"min": 1.029644656794999e-05,
"max": 0.0008437219687593499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114401666666666,
"min": 0.10114401666666666,
"max": 0.19843434999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30343204999999995,
"min": 0.2074766,
"max": 0.5812406500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.708643166666662e-05,
"min": 6.708643166666662e-05,
"max": 0.004921874065,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020125929499999987,
"min": 0.00020125929499999987,
"max": 0.014063908435000001,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1713528406",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1713530903"
},
"total": 2497.4361595500004,
"count": 1,
"self": 0.4506225230002201,
"children": {
"run_training.setup": {
"total": 0.06144342599998254,
"count": 1,
"self": 0.06144342599998254
},
"TrainerController.start_learning": {
"total": 2496.924093601,
"count": 1,
"self": 4.4902361499293875,
"children": {
"TrainerController._reset_env": {
"total": 2.6919980160000705,
"count": 1,
"self": 2.6919980160000705
},
"TrainerController.advance": {
"total": 2489.6289018270704,
"count": 232038,
"self": 4.756521187999169,
"children": {
"env_step": {
"total": 2018.7491395250413,
"count": 232038,
"self": 1676.2097879609714,
"children": {
"SubprocessEnvManager._take_step": {
"total": 339.5622843640407,
"count": 232038,
"self": 17.47411757589373,
"children": {
"TorchPolicy.evaluate": {
"total": 322.08816678814696,
"count": 222965,
"self": 322.08816678814696
}
}
},
"workers": {
"total": 2.9770672000291825,
"count": 232038,
"self": 0.0,
"children": {
"worker_root": {
"total": 2489.6205189499924,
"count": 232038,
"is_parallel": true,
"self": 1135.8903424500377,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008595020000257136,
"count": 1,
"is_parallel": true,
"self": 0.000273306000053708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005861959999720057,
"count": 2,
"is_parallel": true,
"self": 0.0005861959999720057
}
}
},
"UnityEnvironment.step": {
"total": 0.03158755000004021,
"count": 1,
"is_parallel": true,
"self": 0.00039165099997262587,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021935600000233535,
"count": 1,
"is_parallel": true,
"self": 0.00021935600000233535
},
"communicator.exchange": {
"total": 0.030175791000033314,
"count": 1,
"is_parallel": true,
"self": 0.030175791000033314
},
"steps_from_proto": {
"total": 0.0008007520000319346,
"count": 1,
"is_parallel": true,
"self": 0.00022310800011382526,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005776439999181093,
"count": 2,
"is_parallel": true,
"self": 0.0005776439999181093
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1353.7301764999547,
"count": 232037,
"is_parallel": true,
"self": 40.49268304680527,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.9219181200018,
"count": 232037,
"is_parallel": true,
"self": 87.9219181200018
},
"communicator.exchange": {
"total": 1130.6533296270509,
"count": 232037,
"is_parallel": true,
"self": 1130.6533296270509
},
"steps_from_proto": {
"total": 94.66224570609654,
"count": 232037,
"is_parallel": true,
"self": 35.961986150009466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.700259556087076,
"count": 464074,
"is_parallel": true,
"self": 58.700259556087076
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 466.12324111402995,
"count": 232038,
"self": 6.88420532401949,
"children": {
"process_trajectory": {
"total": 157.27348986001334,
"count": 232038,
"self": 155.90782066501276,
"children": {
"RLTrainer._checkpoint": {
"total": 1.365669195000578,
"count": 10,
"self": 1.365669195000578
}
}
},
"_update_policy": {
"total": 301.9655459299971,
"count": 97,
"self": 240.33944950098862,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.6260964290085,
"count": 2910,
"self": 61.6260964290085
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.619999789516442e-07,
"count": 1,
"self": 8.619999789516442e-07
},
"TrainerController._save_models": {
"total": 0.11295674600023631,
"count": 1,
"self": 0.0018849090001822333,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11107183700005407,
"count": 1,
"self": 0.11107183700005407
}
}
}
}
}
}
}