ppo-Huggy / run_logs /timers.json
s94lopez's picture
Huggy
f77be7f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4027860164642334,
"min": 1.4027860164642334,
"max": 1.4289209842681885,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69666.5625,
"min": 67370.5234375,
"max": 78958.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.42206654991243,
"min": 79.91599353796445,
"max": 406.4758064516129,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49347.0,
"min": 48988.0,
"max": 50403.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999262.0,
"min": 49994.0,
"max": 1999262.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999262.0,
"min": 49994.0,
"max": 1999262.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.47627854347229,
"min": 0.06929269433021545,
"max": 2.47627854347229,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1413.955078125,
"min": 8.523001670837402,
"max": 1488.60205078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.867465943463421,
"min": 1.8266153487611592,
"max": 3.87910260535157,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2208.323053717613,
"min": 224.67368789762259,
"max": 2292.493053972721,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.867465943463421,
"min": 1.8266153487611592,
"max": 3.87910260535157,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2208.323053717613,
"min": 224.67368789762259,
"max": 2292.493053972721,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01905736899207113,
"min": 0.013160908617889315,
"max": 0.019856256318174323,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03811473798414226,
"min": 0.02632181723577863,
"max": 0.056687568520222456,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05293659704426924,
"min": 0.020908390109737714,
"max": 0.06748441817859809,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10587319408853849,
"min": 0.04181678021947543,
"max": 0.19335782937705515,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.661423446225005e-06,
"min": 4.661423446225005e-06,
"max": 0.0002952649515783499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.32284689245001e-06,
"min": 9.32284689245001e-06,
"max": 0.000843732018756,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10155377499999999,
"min": 0.10155377499999999,
"max": 0.19842164999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20310754999999997,
"min": 0.20310754999999997,
"max": 0.5812440000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.75333725000001e-05,
"min": 8.75333725000001e-05,
"max": 0.0049212403349999986,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001750667450000002,
"min": 0.0001750667450000002,
"max": 0.014064075599999998,
"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": "1740712878",
"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": "1740715279"
},
"total": 2401.5533889629996,
"count": 1,
"self": 0.6994969899997159,
"children": {
"run_training.setup": {
"total": 0.029722064999987197,
"count": 1,
"self": 0.029722064999987197
},
"TrainerController.start_learning": {
"total": 2400.824169908,
"count": 1,
"self": 4.2075063017500725,
"children": {
"TrainerController._reset_env": {
"total": 3.1503132589998586,
"count": 1,
"self": 3.1503132589998586
},
"TrainerController.advance": {
"total": 2393.2979278342505,
"count": 231943,
"self": 4.469585520243982,
"children": {
"env_step": {
"total": 1910.5190012039502,
"count": 231943,
"self": 1496.6282322490551,
"children": {
"SubprocessEnvManager._take_step": {
"total": 411.31273518594503,
"count": 231943,
"self": 15.50339070298105,
"children": {
"TorchPolicy.evaluate": {
"total": 395.809344482964,
"count": 222866,
"self": 395.809344482964
}
}
},
"workers": {
"total": 2.5780337689500357,
"count": 231943,
"self": 0.0,
"children": {
"worker_root": {
"total": 2393.469713767093,
"count": 231943,
"is_parallel": true,
"self": 1171.3147124221707,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012945919997946476,
"count": 1,
"is_parallel": true,
"self": 0.00029107199998179567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001003519999812852,
"count": 2,
"is_parallel": true,
"self": 0.001003519999812852
}
}
},
"UnityEnvironment.step": {
"total": 0.030723822000027212,
"count": 1,
"is_parallel": true,
"self": 0.000330290999954741,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019771500001297682,
"count": 1,
"is_parallel": true,
"self": 0.00019771500001297682
},
"communicator.exchange": {
"total": 0.02949211500003912,
"count": 1,
"is_parallel": true,
"self": 0.02949211500003912
},
"steps_from_proto": {
"total": 0.0007037010000203736,
"count": 1,
"is_parallel": true,
"self": 0.0001779720000740781,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005257289999462955,
"count": 2,
"is_parallel": true,
"self": 0.0005257289999462955
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1222.155001344922,
"count": 231942,
"is_parallel": true,
"self": 36.525857481799676,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.94203916890933,
"count": 231942,
"is_parallel": true,
"self": 80.94203916890933
},
"communicator.exchange": {
"total": 1018.2481032392211,
"count": 231942,
"is_parallel": true,
"self": 1018.2481032392211
},
"steps_from_proto": {
"total": 86.43900145499197,
"count": 231942,
"is_parallel": true,
"self": 31.86911806964349,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.569883385348476,
"count": 463884,
"is_parallel": true,
"self": 54.569883385348476
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 478.30934111005627,
"count": 231943,
"self": 6.065605098014657,
"children": {
"process_trajectory": {
"total": 157.86141306704462,
"count": 231943,
"self": 156.42907895504527,
"children": {
"RLTrainer._checkpoint": {
"total": 1.432334111999353,
"count": 10,
"self": 1.432334111999353
}
}
},
"_update_policy": {
"total": 314.382322944997,
"count": 96,
"self": 250.38735138098627,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.99497156401071,
"count": 2880,
"self": 63.99497156401071
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1789998097810894e-06,
"count": 1,
"self": 1.1789998097810894e-06
},
"TrainerController._save_models": {
"total": 0.16842133399950399,
"count": 1,
"self": 0.0028427609995560488,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16557857299994794,
"count": 1,
"self": 0.16557857299994794
}
}
}
}
}
}
}