ppo-Huggy / run_logs /timers.json
Ankit Kumar
Huggy
79f667d
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.402930736541748,
"min": 1.402930736541748,
"max": 1.4292300939559937,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68691.6953125,
"min": 68667.8203125,
"max": 78141.8984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.6328125,
"min": 86.77288732394366,
"max": 362.22463768115944,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49476.0,
"min": 49234.0,
"max": 49987.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999966.0,
"min": 49850.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999966.0,
"min": 49850.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3856208324432373,
"min": 0.03630569949746132,
"max": 2.483292818069458,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1221.4378662109375,
"min": 4.973880767822266,
"max": 1348.205810546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6445855729980394,
"min": 1.780133055509442,
"max": 3.9068084628351274,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1866.0278133749962,
"min": 243.87822860479355,
"max": 2092.4930084347725,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6445855729980394,
"min": 1.780133055509442,
"max": 3.9068084628351274,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1866.0278133749962,
"min": 243.87822860479355,
"max": 2092.4930084347725,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014371680280762827,
"min": 0.014371680280762827,
"max": 0.020269497162856472,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04311504084228848,
"min": 0.02935734612401575,
"max": 0.06080849148856942,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04872748160527812,
"min": 0.023898275258640446,
"max": 0.055869820755388995,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14618244481583437,
"min": 0.04779655051728089,
"max": 0.167609462266167,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4062488646166746e-06,
"min": 3.4062488646166746e-06,
"max": 0.00029534512655162495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0218746593850024e-05,
"min": 1.0218746593850024e-05,
"max": 0.0008438548687150499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113538333333334,
"min": 0.10113538333333334,
"max": 0.198448375,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30340615000000004,
"min": 0.20742,
"max": 0.5812849499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.665562833333347e-05,
"min": 6.665562833333347e-05,
"max": 0.004922573912499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019996688500000044,
"min": 0.00019996688500000044,
"max": 0.014066119004999999,
"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": "1694898418",
"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",
"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": "1694901076"
},
"total": 2658.4742837719996,
"count": 1,
"self": 0.4409288289994038,
"children": {
"run_training.setup": {
"total": 0.0434546159999627,
"count": 1,
"self": 0.0434546159999627
},
"TrainerController.start_learning": {
"total": 2657.989900327,
"count": 1,
"self": 4.983771158043055,
"children": {
"TrainerController._reset_env": {
"total": 4.370354708000036,
"count": 1,
"self": 4.370354708000036
},
"TrainerController.advance": {
"total": 2648.5046863409575,
"count": 231987,
"self": 5.183460191043196,
"children": {
"env_step": {
"total": 2051.1284873289046,
"count": 231987,
"self": 1733.7138863318205,
"children": {
"SubprocessEnvManager._take_step": {
"total": 314.1391703380842,
"count": 231987,
"self": 18.64944449504401,
"children": {
"TorchPolicy.evaluate": {
"total": 295.4897258430402,
"count": 222915,
"self": 295.4897258430402
}
}
},
"workers": {
"total": 3.2754306589998805,
"count": 231987,
"self": 0.0,
"children": {
"worker_root": {
"total": 2649.7096440580804,
"count": 231987,
"is_parallel": true,
"self": 1228.9932860222398,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009582730000374795,
"count": 1,
"is_parallel": true,
"self": 0.0002741970000670335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000684075999970446,
"count": 2,
"is_parallel": true,
"self": 0.000684075999970446
}
}
},
"UnityEnvironment.step": {
"total": 0.03030646499996692,
"count": 1,
"is_parallel": true,
"self": 0.00038366499995845516,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024518099996839737,
"count": 1,
"is_parallel": true,
"self": 0.00024518099996839737
},
"communicator.exchange": {
"total": 0.028865470000027926,
"count": 1,
"is_parallel": true,
"self": 0.028865470000027926
},
"steps_from_proto": {
"total": 0.0008121490000121412,
"count": 1,
"is_parallel": true,
"self": 0.00021915599995736557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005929930000547756,
"count": 2,
"is_parallel": true,
"self": 0.0005929930000547756
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1420.7163580358406,
"count": 231986,
"is_parallel": true,
"self": 43.12270459190745,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.84029209806727,
"count": 231986,
"is_parallel": true,
"self": 85.84029209806727
},
"communicator.exchange": {
"total": 1185.0409143590084,
"count": 231986,
"is_parallel": true,
"self": 1185.0409143590084
},
"steps_from_proto": {
"total": 106.71244698685746,
"count": 231986,
"is_parallel": true,
"self": 37.23239801602142,
"children": {
"_process_rank_one_or_two_observation": {
"total": 69.48004897083604,
"count": 463972,
"is_parallel": true,
"self": 69.48004897083604
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 592.1927388210098,
"count": 231987,
"self": 7.343979679973472,
"children": {
"process_trajectory": {
"total": 145.38912458003563,
"count": 231987,
"self": 144.01280381803508,
"children": {
"RLTrainer._checkpoint": {
"total": 1.376320762000546,
"count": 10,
"self": 1.376320762000546
}
}
},
"_update_policy": {
"total": 439.4596345610007,
"count": 97,
"self": 375.7914772760056,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.66815728499512,
"count": 2910,
"self": 63.66815728499512
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.93999947240809e-07,
"count": 1,
"self": 9.93999947240809e-07
},
"TrainerController._save_models": {
"total": 0.1310871259997839,
"count": 1,
"self": 0.002013400000123511,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12907372599966038,
"count": 1,
"self": 0.12907372599966038
}
}
}
}
}
}
}