Vadu's picture
Huggy's first hug
e348b6e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4077717065811157,
"min": 1.4077717065811157,
"max": 1.430090308189392,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71379.65625,
"min": 69459.03125,
"max": 77832.796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.31260794473229,
"min": 74.85151515151514,
"max": 426.1779661016949,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49396.0,
"min": 48874.0,
"max": 50289.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999962.0,
"min": 49987.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999962.0,
"min": 49987.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4085440635681152,
"min": 0.08533310890197754,
"max": 2.4759910106658936,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1394.5469970703125,
"min": 9.983973503112793,
"max": 1564.872802734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.74170178586749,
"min": 1.74851012790305,
"max": 4.099366782375218,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2166.4453340172768,
"min": 204.57568496465683,
"max": 2484.9020253419876,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.74170178586749,
"min": 1.74851012790305,
"max": 4.099366782375218,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2166.4453340172768,
"min": 204.57568496465683,
"max": 2484.9020253419876,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014998338322271189,
"min": 0.013094147973667229,
"max": 0.01923316070266689,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04499501496681357,
"min": 0.026188295947334458,
"max": 0.05761544112174306,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05670261225766606,
"min": 0.020814772695302963,
"max": 0.06146399596085152,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17010783677299818,
"min": 0.041629545390605927,
"max": 0.1716800007969141,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.509748830116664e-06,
"min": 3.509748830116664e-06,
"max": 0.00029538750153749994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0529246490349992e-05,
"min": 1.0529246490349992e-05,
"max": 0.0008442105185964999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116988333333332,
"min": 0.10116988333333332,
"max": 0.19846250000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30350964999999996,
"min": 0.20749689999999996,
"max": 0.5814035,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.83771783333333e-05,
"min": 6.83771783333333e-05,
"max": 0.004923278749999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002051315349999999,
"min": 0.0002051315349999999,
"max": 0.014072034649999999,
"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": "1694354901",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1694357335"
},
"total": 2433.850054669,
"count": 1,
"self": 0.42730162800080507,
"children": {
"run_training.setup": {
"total": 0.03895400399960636,
"count": 1,
"self": 0.03895400399960636
},
"TrainerController.start_learning": {
"total": 2433.383799037,
"count": 1,
"self": 4.34575657692767,
"children": {
"TrainerController._reset_env": {
"total": 3.836951196999962,
"count": 1,
"self": 3.836951196999962
},
"TrainerController.advance": {
"total": 2425.0777676430725,
"count": 232676,
"self": 4.414784320760191,
"children": {
"env_step": {
"total": 1853.0544218521532,
"count": 232676,
"self": 1564.9912060761862,
"children": {
"SubprocessEnvManager._take_step": {
"total": 285.1866737509981,
"count": 232676,
"self": 16.46966241922337,
"children": {
"TorchPolicy.evaluate": {
"total": 268.71701133177476,
"count": 223014,
"self": 268.71701133177476
}
}
},
"workers": {
"total": 2.876542024968785,
"count": 232676,
"self": 0.0,
"children": {
"worker_root": {
"total": 2425.832766437204,
"count": 232676,
"is_parallel": true,
"self": 1149.1085526563602,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008199609997063817,
"count": 1,
"is_parallel": true,
"self": 0.0002201329998570145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005998279998493672,
"count": 2,
"is_parallel": true,
"self": 0.0005998279998493672
}
}
},
"UnityEnvironment.step": {
"total": 0.028850290999798744,
"count": 1,
"is_parallel": true,
"self": 0.0002973679997921863,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023758699990139576,
"count": 1,
"is_parallel": true,
"self": 0.00023758699990139576
},
"communicator.exchange": {
"total": 0.027587302000029013,
"count": 1,
"is_parallel": true,
"self": 0.027587302000029013
},
"steps_from_proto": {
"total": 0.0007280340000761498,
"count": 1,
"is_parallel": true,
"self": 0.0002181200002269179,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005099139998492319,
"count": 2,
"is_parallel": true,
"self": 0.0005099139998492319
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1276.724213780844,
"count": 232675,
"is_parallel": true,
"self": 38.942182222363954,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.2568522401184,
"count": 232675,
"is_parallel": true,
"self": 80.2568522401184
},
"communicator.exchange": {
"total": 1060.2065792091416,
"count": 232675,
"is_parallel": true,
"self": 1060.2065792091416
},
"steps_from_proto": {
"total": 97.31860010921991,
"count": 232675,
"is_parallel": true,
"self": 34.5907466513072,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.727853457912715,
"count": 465350,
"is_parallel": true,
"self": 62.727853457912715
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 567.6085614701592,
"count": 232676,
"self": 6.509504214420758,
"children": {
"process_trajectory": {
"total": 138.75106664173472,
"count": 232676,
"self": 137.4001871837354,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3508794579993264,
"count": 10,
"self": 1.3508794579993264
}
}
},
"_update_policy": {
"total": 422.3479906140037,
"count": 97,
"self": 360.76326511400384,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.58472549999988,
"count": 2910,
"self": 61.58472549999988
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.659997886046767e-07,
"count": 1,
"self": 9.659997886046767e-07
},
"TrainerController._save_models": {
"total": 0.12332265399982134,
"count": 1,
"self": 0.002564888000051724,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12075776599976962,
"count": 1,
"self": 0.12075776599976962
}
}
}
}
}
}
}