ppo-Huggy / run_logs /timers.json
CrazyAIGC's picture
Huggy
0cff07b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4031397104263306,
"min": 1.4031397104263306,
"max": 1.4269880056381226,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69794.9765625,
"min": 67943.4296875,
"max": 79214.578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.13414634146342,
"min": 81.66390728476821,
"max": 399.07142857142856,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49266.0,
"min": 48777.0,
"max": 50283.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999989.0,
"min": 49955.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999989.0,
"min": 49955.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.394756555557251,
"min": 0.13673676550388336,
"max": 2.4428985118865967,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1178.22021484375,
"min": 17.09209632873535,
"max": 1437.688232421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.650208164884792,
"min": 1.8146934875249863,
"max": 3.927029551606472,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1795.9024171233177,
"min": 226.83668594062328,
"max": 2293.38525813818,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.650208164884792,
"min": 1.8146934875249863,
"max": 3.927029551606472,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1795.9024171233177,
"min": 226.83668594062328,
"max": 2293.38525813818,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015802983740811922,
"min": 0.013523310038403402,
"max": 0.020624932219895226,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04740895122243576,
"min": 0.028669181724641626,
"max": 0.05859787239266249,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05097094492779838,
"min": 0.02201711302623153,
"max": 0.06281777601689101,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15291283478339512,
"min": 0.04403422605246306,
"max": 0.17079066249231498,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5566988144666655e-06,
"min": 3.5566988144666655e-06,
"max": 0.000295342126552625,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0670096443399997e-05,
"min": 1.0670096443399997e-05,
"max": 0.0008441481186172999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118553333333334,
"min": 0.10118553333333334,
"max": 0.19844737499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035566,
"min": 0.20751750000000008,
"max": 0.5813827,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.915811333333331e-05,
"min": 6.915811333333331e-05,
"max": 0.0049225240125,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020747433999999991,
"min": 0.00020747433999999991,
"max": 0.01407099673,
"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": "1739447512",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739450004"
},
"total": 2491.686157022,
"count": 1,
"self": 0.4407596150003883,
"children": {
"run_training.setup": {
"total": 0.023432111999909466,
"count": 1,
"self": 0.023432111999909466
},
"TrainerController.start_learning": {
"total": 2491.221965295,
"count": 1,
"self": 4.427834182973584,
"children": {
"TrainerController._reset_env": {
"total": 2.947015570999838,
"count": 1,
"self": 2.947015570999838
},
"TrainerController.advance": {
"total": 2483.727104705027,
"count": 232778,
"self": 4.9356977630286565,
"children": {
"env_step": {
"total": 1994.11897913097,
"count": 232778,
"self": 1567.215039225996,
"children": {
"SubprocessEnvManager._take_step": {
"total": 424.17555019006295,
"count": 232778,
"self": 16.21005820904179,
"children": {
"TorchPolicy.evaluate": {
"total": 407.96549198102116,
"count": 223044,
"self": 407.96549198102116
}
}
},
"workers": {
"total": 2.7283897149111453,
"count": 232778,
"self": 0.0,
"children": {
"worker_root": {
"total": 2483.4987439059805,
"count": 232778,
"is_parallel": true,
"self": 1207.3547946548506,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011257930000283523,
"count": 1,
"is_parallel": true,
"self": 0.00043916600020565966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006866269998226926,
"count": 2,
"is_parallel": true,
"self": 0.0006866269998226926
}
}
},
"UnityEnvironment.step": {
"total": 0.03418361300009565,
"count": 1,
"is_parallel": true,
"self": 0.000317555000037828,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019079499998042593,
"count": 1,
"is_parallel": true,
"self": 0.00019079499998042593
},
"communicator.exchange": {
"total": 0.0329233600000407,
"count": 1,
"is_parallel": true,
"self": 0.0329233600000407
},
"steps_from_proto": {
"total": 0.0007519030000366911,
"count": 1,
"is_parallel": true,
"self": 0.0002314129999376746,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005204900000990165,
"count": 2,
"is_parallel": true,
"self": 0.0005204900000990165
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1276.14394925113,
"count": 232777,
"is_parallel": true,
"self": 38.07566101993734,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.48805133812198,
"count": 232777,
"is_parallel": true,
"self": 82.48805133812198
},
"communicator.exchange": {
"total": 1066.7023636579943,
"count": 232777,
"is_parallel": true,
"self": 1066.7023636579943
},
"steps_from_proto": {
"total": 88.87787323507632,
"count": 232777,
"is_parallel": true,
"self": 32.91593649099377,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.96193674408255,
"count": 465554,
"is_parallel": true,
"self": 55.96193674408255
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 484.67242781102823,
"count": 232778,
"self": 6.633902131895638,
"children": {
"process_trajectory": {
"total": 167.96649915113449,
"count": 232778,
"self": 166.56784783513376,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3986513160007235,
"count": 10,
"self": 1.3986513160007235
}
}
},
"_update_policy": {
"total": 310.0720265279981,
"count": 97,
"self": 245.45298014901005,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.61904637898806,
"count": 2910,
"self": 64.61904637898806
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.329996828455478e-07,
"count": 1,
"self": 9.329996828455478e-07
},
"TrainerController._save_models": {
"total": 0.12000990299975456,
"count": 1,
"self": 0.001823948999572167,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11818595400018239,
"count": 1,
"self": 0.11818595400018239
}
}
}
}
}
}
}