ppo-Huggy / run_logs /timers.json
ernestwasi's picture
Huggy
8dde0fa verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4034978151321411,
"min": 1.4034978151321411,
"max": 1.4274362325668335,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70229.625,
"min": 66860.71875,
"max": 77013.828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.34375,
"min": 75.33740458015266,
"max": 395.0859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49457.0,
"min": 48813.0,
"max": 50571.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999350.0,
"min": 49949.0,
"max": 1999350.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999350.0,
"min": 49949.0,
"max": 1999350.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.515976667404175,
"min": 0.0687936395406723,
"max": 2.5305657386779785,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1529.7138671875,
"min": 8.73679256439209,
"max": 1643.63720703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8808212769462873,
"min": 1.693990797625752,
"max": 4.05619676980829,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2359.5393363833427,
"min": 215.1368312984705,
"max": 2537.731083035469,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8808212769462873,
"min": 1.693990797625752,
"max": 4.05619676980829,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2359.5393363833427,
"min": 215.1368312984705,
"max": 2537.731083035469,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017343712802458968,
"min": 0.012718278943308785,
"max": 0.021790537680256725,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0520311384073769,
"min": 0.02543655788661757,
"max": 0.057714747212594376,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06273944733871355,
"min": 0.022030143532902002,
"max": 0.06499364009747902,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18821834201614063,
"min": 0.044060287065804005,
"max": 0.1908846548448006,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.556298814599987e-06,
"min": 3.556298814599987e-06,
"max": 0.00029537572654142496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0668896443799961e-05,
"min": 1.0668896443799961e-05,
"max": 0.0008441652186116,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011854,
"min": 0.1011854,
"max": 0.19845857500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035562,
"min": 0.20753184999999993,
"max": 0.5813884,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.915145999999979e-05,
"min": 6.915145999999979e-05,
"max": 0.0049230828925,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020745437999999936,
"min": 0.00020745437999999936,
"max": 0.014071281159999999,
"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": "1718352606",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718357202"
},
"total": 4596.245404982999,
"count": 1,
"self": 0.8214203719999205,
"children": {
"run_training.setup": {
"total": 0.07772125799999685,
"count": 1,
"self": 0.07772125799999685
},
"TrainerController.start_learning": {
"total": 4595.346263353,
"count": 1,
"self": 8.48519611008578,
"children": {
"TrainerController._reset_env": {
"total": 4.023542016999954,
"count": 1,
"self": 4.023542016999954
},
"TrainerController.advance": {
"total": 4582.721090192914,
"count": 233002,
"self": 8.392850619147794,
"children": {
"env_step": {
"total": 2980.522367097893,
"count": 233002,
"self": 2500.549311518993,
"children": {
"SubprocessEnvManager._take_step": {
"total": 474.54432894297145,
"count": 233002,
"self": 31.5121603978821,
"children": {
"TorchPolicy.evaluate": {
"total": 443.03216854508935,
"count": 222932,
"self": 443.03216854508935
}
}
},
"workers": {
"total": 5.428726635928456,
"count": 233002,
"self": 0.0,
"children": {
"worker_root": {
"total": 4581.474635104818,
"count": 233002,
"is_parallel": true,
"self": 2605.9320316528665,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012179990000049656,
"count": 1,
"is_parallel": true,
"self": 0.0003032110000731336,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000914787999931832,
"count": 2,
"is_parallel": true,
"self": 0.000914787999931832
}
}
},
"UnityEnvironment.step": {
"total": 0.040118301000006795,
"count": 1,
"is_parallel": true,
"self": 0.0005118779998838363,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002561249999644133,
"count": 1,
"is_parallel": true,
"self": 0.0002561249999644133
},
"communicator.exchange": {
"total": 0.03834918700010803,
"count": 1,
"is_parallel": true,
"self": 0.03834918700010803
},
"steps_from_proto": {
"total": 0.0010011110000505141,
"count": 1,
"is_parallel": true,
"self": 0.0002878040000950932,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007133069999554209,
"count": 2,
"is_parallel": true,
"self": 0.0007133069999554209
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1975.5426034519514,
"count": 233001,
"is_parallel": true,
"self": 64.15329255768256,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 111.32561811015978,
"count": 233001,
"is_parallel": true,
"self": 111.32561811015978
},
"communicator.exchange": {
"total": 1662.1989083260914,
"count": 233001,
"is_parallel": true,
"self": 1662.1989083260914
},
"steps_from_proto": {
"total": 137.86478445801777,
"count": 233001,
"is_parallel": true,
"self": 44.86022242814795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 93.00456202986982,
"count": 466002,
"is_parallel": true,
"self": 93.00456202986982
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1593.8058724758735,
"count": 233002,
"self": 13.065629085865567,
"children": {
"process_trajectory": {
"total": 257.6117814490059,
"count": 233002,
"self": 256.325992201006,
"children": {
"RLTrainer._checkpoint": {
"total": 1.285789247999901,
"count": 10,
"self": 1.285789247999901
}
}
},
"_update_policy": {
"total": 1323.1284619410021,
"count": 97,
"self": 350.90415536900014,
"children": {
"TorchPPOOptimizer.update": {
"total": 972.224306572002,
"count": 2910,
"self": 972.224306572002
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1419997463235632e-06,
"count": 1,
"self": 1.1419997463235632e-06
},
"TrainerController._save_models": {
"total": 0.1164338910002698,
"count": 1,
"self": 0.0029719499998464016,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1134619410004234,
"count": 1,
"self": 0.1134619410004234
}
}
}
}
}
}
}