ppo-Huggy / run_logs /timers.json
LakshGupta's picture
Huggy
1c9afb0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4078997373580933,
"min": 1.4078997373580933,
"max": 1.429194450378418,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68453.4921875,
"min": 68453.4921875,
"max": 75833.984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.16931216931216,
"min": 81.53731343283582,
"max": 388.1782945736434,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49425.0,
"min": 49011.0,
"max": 50075.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999957.0,
"min": 49577.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999957.0,
"min": 49577.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.389970541000366,
"min": 0.18830406665802002,
"max": 2.453549861907959,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1355.11328125,
"min": 24.102920532226562,
"max": 1433.8050537109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6673783704086587,
"min": 1.7740916362963617,
"max": 3.9435425297073694,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2079.4035360217094,
"min": 227.0837294459343,
"max": 2282.348513364792,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6673783704086587,
"min": 1.7740916362963617,
"max": 3.9435425297073694,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2079.4035360217094,
"min": 227.0837294459343,
"max": 2282.348513364792,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015764328319993286,
"min": 0.013986057816237008,
"max": 0.022182538183794044,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047292984959979856,
"min": 0.027972115632474016,
"max": 0.05367791880465423,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05626912638545036,
"min": 0.020377401096953286,
"max": 0.06125467903912067,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16880737915635108,
"min": 0.04486088783790668,
"max": 0.1735705751925707,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3911988696333365e-06,
"min": 3.3911988696333365e-06,
"max": 0.00029529120156960003,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.017359660890001e-05,
"min": 1.017359660890001e-05,
"max": 0.0008439343686885501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113036666666668,
"min": 0.10113036666666668,
"max": 0.19843039999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033911,
"min": 0.2073936,
"max": 0.5813114500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.640529666666671e-05,
"min": 6.640529666666671e-05,
"max": 0.004921676960000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019921589000000014,
"min": 0.00019921589000000014,
"max": 0.014067441355000002,
"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": "1750063632",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750066082"
},
"total": 2450.375411226,
"count": 1,
"self": 0.4384429239999008,
"children": {
"run_training.setup": {
"total": 0.03075571499994112,
"count": 1,
"self": 0.03075571499994112
},
"TrainerController.start_learning": {
"total": 2449.906212587,
"count": 1,
"self": 4.188300891964445,
"children": {
"TrainerController._reset_env": {
"total": 3.746164130000011,
"count": 1,
"self": 3.746164130000011
},
"TrainerController.advance": {
"total": 2441.8652654740354,
"count": 232058,
"self": 4.358216962054485,
"children": {
"env_step": {
"total": 1950.6500211990028,
"count": 232058,
"self": 1545.702639899851,
"children": {
"SubprocessEnvManager._take_step": {
"total": 402.36122001113165,
"count": 232058,
"self": 15.520659530185753,
"children": {
"TorchPolicy.evaluate": {
"total": 386.8405604809459,
"count": 222875,
"self": 386.8405604809459
}
}
},
"workers": {
"total": 2.586161288020321,
"count": 232058,
"self": 0.0,
"children": {
"worker_root": {
"total": 2442.3514553742043,
"count": 232058,
"is_parallel": true,
"self": 1179.2773243532488,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009393459999955667,
"count": 1,
"is_parallel": true,
"self": 0.00026535599999988335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006739899999956833,
"count": 2,
"is_parallel": true,
"self": 0.0006739899999956833
}
}
},
"UnityEnvironment.step": {
"total": 0.051303078999922036,
"count": 1,
"is_parallel": true,
"self": 0.00032853799984877696,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002257990000771315,
"count": 1,
"is_parallel": true,
"self": 0.0002257990000771315
},
"communicator.exchange": {
"total": 0.05003560199997992,
"count": 1,
"is_parallel": true,
"self": 0.05003560199997992
},
"steps_from_proto": {
"total": 0.0007131400000162103,
"count": 1,
"is_parallel": true,
"self": 0.00020044699999743898,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005126930000187713,
"count": 2,
"is_parallel": true,
"self": 0.0005126930000187713
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1263.0741310209555,
"count": 232057,
"is_parallel": true,
"self": 37.50299813886659,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.40142685300873,
"count": 232057,
"is_parallel": true,
"self": 81.40142685300873
},
"communicator.exchange": {
"total": 1056.123688365034,
"count": 232057,
"is_parallel": true,
"self": 1056.123688365034
},
"steps_from_proto": {
"total": 88.04601766404642,
"count": 232057,
"is_parallel": true,
"self": 30.767357758996354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.27865990505006,
"count": 464114,
"is_parallel": true,
"self": 57.27865990505006
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 486.8570273129782,
"count": 232058,
"self": 6.334529312002019,
"children": {
"process_trajectory": {
"total": 156.65584088897663,
"count": 232058,
"self": 155.3376901319764,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3181507570002395,
"count": 10,
"self": 1.3181507570002395
}
}
},
"_update_policy": {
"total": 323.86665711199953,
"count": 97,
"self": 259.6496233360094,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.2170337759901,
"count": 2910,
"self": 64.2170337759901
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4350002857099753e-06,
"count": 1,
"self": 1.4350002857099753e-06
},
"TrainerController._save_models": {
"total": 0.10648065599980328,
"count": 1,
"self": 0.002518328999485675,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1039623270003176,
"count": 1,
"self": 0.1039623270003176
}
}
}
}
}
}
}