ppo-Huggy / run_logs /timers.json
amangoyal's picture
Huggy
ca7c4b1
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407238483428955,
"min": 1.407238483428955,
"max": 1.427427887916565,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71079.6171875,
"min": 68671.828125,
"max": 77461.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.51689189189189,
"min": 76.75545171339564,
"max": 420.1666666666667,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49442.0,
"min": 48984.0,
"max": 50420.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999929.0,
"min": 49952.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999929.0,
"min": 49952.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3864142894744873,
"min": 0.1120530441403389,
"max": 2.4970903396606445,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1412.75732421875,
"min": 13.334312438964844,
"max": 1537.3792724609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.752220701829002,
"min": 1.8300812765329826,
"max": 4.020239795272182,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2221.314655482769,
"min": 217.77967190742493,
"max": 2448.326035320759,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.752220701829002,
"min": 1.8300812765329826,
"max": 4.020239795272182,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2221.314655482769,
"min": 217.77967190742493,
"max": 2448.326035320759,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01662087877565581,
"min": 0.012959048224972017,
"max": 0.020431991134925435,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04986263632696743,
"min": 0.025918096449944035,
"max": 0.055281779726404544,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05439433476163281,
"min": 0.020832082722336054,
"max": 0.05935835416118304,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16318300428489843,
"min": 0.04166416544467211,
"max": 0.17807506248354912,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.76459874516667e-06,
"min": 3.76459874516667e-06,
"max": 0.000295328026557325,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.129379623550001e-05,
"min": 1.129379623550001e-05,
"max": 0.0008442318185893998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125483333333331,
"min": 0.10125483333333331,
"max": 0.19844267499999999,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30376449999999994,
"min": 0.20767344999999993,
"max": 0.5814106,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.26161833333334e-05,
"min": 7.26161833333334e-05,
"max": 0.0049222894825,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002178485500000002,
"min": 0.0002178485500000002,
"max": 0.014072388940000001,
"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": "1670417277",
"python_version": "3.8.15 | packaged by conda-forge | (default, Nov 22 2022, 08:49:35) \n[GCC 10.4.0]",
"command_line_arguments": "/home/ubuntu/mambaforge/envs/sb3_38/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.13.0",
"numpy_version": "1.23.5",
"end_time_seconds": "1670419800"
},
"total": 2522.9838362619976,
"count": 1,
"self": 7.180253682998227,
"children": {
"run_training.setup": {
"total": 0.10888429900114716,
"count": 1,
"self": 0.10888429900114716
},
"TrainerController.start_learning": {
"total": 2515.694698279998,
"count": 1,
"self": 4.777466131541587,
"children": {
"TrainerController._reset_env": {
"total": 25.5694899909995,
"count": 1,
"self": 25.5694899909995
},
"TrainerController.advance": {
"total": 2484.058282328453,
"count": 232612,
"self": 4.494313233297362,
"children": {
"env_step": {
"total": 1929.31561146083,
"count": 232612,
"self": 1493.067952422136,
"children": {
"SubprocessEnvManager._take_step": {
"total": 432.99438598997403,
"count": 232612,
"self": 14.678683317504692,
"children": {
"TorchPolicy.evaluate": {
"total": 418.31570267246934,
"count": 222974,
"self": 164.74300916544416,
"children": {
"TorchPolicy.sample_actions": {
"total": 253.57269350702518,
"count": 222974,
"self": 253.57269350702518
}
}
}
}
},
"workers": {
"total": 3.253273048720075,
"count": 232612,
"self": 0.0,
"children": {
"worker_root": {
"total": 2504.440215493123,
"count": 232612,
"is_parallel": true,
"self": 1509.638435858722,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007180969987530261,
"count": 1,
"is_parallel": true,
"self": 0.00023298699670704082,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004851100020459853,
"count": 2,
"is_parallel": true,
"self": 0.0004851100020459853
}
}
},
"UnityEnvironment.step": {
"total": 0.060094640000897925,
"count": 1,
"is_parallel": true,
"self": 0.00023997000062081497,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019759099996008445,
"count": 1,
"is_parallel": true,
"self": 0.00019759099996008445
},
"communicator.exchange": {
"total": 0.0591502989991568,
"count": 1,
"is_parallel": true,
"self": 0.0591502989991568
},
"steps_from_proto": {
"total": 0.000506780001160223,
"count": 1,
"is_parallel": true,
"self": 0.00019149000036122743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003152900007989956,
"count": 2,
"is_parallel": true,
"self": 0.0003152900007989956
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 994.8017796344011,
"count": 232611,
"is_parallel": true,
"self": 24.094431404184434,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 41.805580481630386,
"count": 232611,
"is_parallel": true,
"self": 41.805580481630386
},
"communicator.exchange": {
"total": 874.8659401897585,
"count": 232611,
"is_parallel": true,
"self": 874.8659401897585
},
"steps_from_proto": {
"total": 54.035827558827805,
"count": 232611,
"is_parallel": true,
"self": 20.428174569733528,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.60765298909428,
"count": 465222,
"is_parallel": true,
"self": 33.60765298909428
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 550.2483576343257,
"count": 232612,
"self": 7.754822472081287,
"children": {
"process_trajectory": {
"total": 211.00731228923905,
"count": 232612,
"self": 208.96266401723915,
"children": {
"RLTrainer._checkpoint": {
"total": 2.044648271999904,
"count": 4,
"self": 2.044648271999904
}
}
},
"_update_policy": {
"total": 331.4862228730053,
"count": 97,
"self": 258.54193202999886,
"children": {
"TorchPPOOptimizer.update": {
"total": 72.94429084300646,
"count": 2910,
"self": 72.94429084300646
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0220028343610466e-06,
"count": 1,
"self": 1.0220028343610466e-06
},
"TrainerController._save_models": {
"total": 1.2894588070012105,
"count": 1,
"self": 0.3128243589999329,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9766344480012776,
"count": 1,
"self": 0.9766344480012776
}
}
}
}
}
}
}