ppo-Huggy / run_logs /timers.json
Giuseppe Frigeni
Huggy
00f13ea
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3965619802474976,
"min": 1.3965619802474976,
"max": 1.4231648445129395,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70797.3125,
"min": 67314.75,
"max": 78822.703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.8739837398374,
"min": 87.56814159292036,
"max": 386.984496124031,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49630.0,
"min": 48972.0,
"max": 50060.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999408.0,
"min": 49912.0,
"max": 1999408.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999408.0,
"min": 49912.0,
"max": 1999408.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.347548007965088,
"min": 0.05735760182142258,
"max": 2.4565579891204834,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1154.99365234375,
"min": 7.34177303314209,
"max": 1353.5623779296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.60518400249927,
"min": 1.7561396334785968,
"max": 3.932191999510651,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1773.750529229641,
"min": 224.7858730852604,
"max": 2136.2822848558426,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.60518400249927,
"min": 1.7561396334785968,
"max": 3.932191999510651,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1773.750529229641,
"min": 224.7858730852604,
"max": 2136.2822848558426,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01770239641256113,
"min": 0.013501493026463626,
"max": 0.020791027679418525,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05310718923768339,
"min": 0.027002986052927253,
"max": 0.05971309991631036,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05081976445184813,
"min": 0.021450686672081547,
"max": 0.05581834906091293,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1524592933555444,
"min": 0.04290137334416309,
"max": 0.16581338780621688,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3715988761666704e-06,
"min": 3.3715988761666704e-06,
"max": 0.00029536575154474995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0114796628500011e-05,
"min": 1.0114796628500011e-05,
"max": 0.0008442147185950999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112383333333332,
"min": 0.10112383333333332,
"max": 0.19845524999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30337149999999996,
"min": 0.20738919999999994,
"max": 0.5814049,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.607928333333343e-05,
"min": 6.607928333333343e-05,
"max": 0.004922916974999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019823785000000027,
"min": 0.00019823785000000027,
"max": 0.014072104510000003,
"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": "1691949869",
"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": "1691952266"
},
"total": 2396.4189597590002,
"count": 1,
"self": 0.7791486270002679,
"children": {
"run_training.setup": {
"total": 0.04298198500003991,
"count": 1,
"self": 0.04298198500003991
},
"TrainerController.start_learning": {
"total": 2395.596829147,
"count": 1,
"self": 4.262818693066038,
"children": {
"TrainerController._reset_env": {
"total": 4.679265553999983,
"count": 1,
"self": 4.679265553999983
},
"TrainerController.advance": {
"total": 2386.4695411469343,
"count": 231905,
"self": 4.504145170928041,
"children": {
"env_step": {
"total": 1845.115959004947,
"count": 231905,
"self": 1559.0657301481583,
"children": {
"SubprocessEnvManager._take_step": {
"total": 283.17788878583514,
"count": 231905,
"self": 16.00060289287609,
"children": {
"TorchPolicy.evaluate": {
"total": 267.17728589295905,
"count": 222990,
"self": 267.17728589295905
}
}
},
"workers": {
"total": 2.8723400709534985,
"count": 231905,
"self": 0.0,
"children": {
"worker_root": {
"total": 2388.1462741209793,
"count": 231905,
"is_parallel": true,
"self": 1113.0460795589324,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008914599999911843,
"count": 1,
"is_parallel": true,
"self": 0.0003110870000000432,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005803729999911411,
"count": 2,
"is_parallel": true,
"self": 0.0005803729999911411
}
}
},
"UnityEnvironment.step": {
"total": 0.04473410400004241,
"count": 1,
"is_parallel": true,
"self": 0.0003745170000684084,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002324889999840707,
"count": 1,
"is_parallel": true,
"self": 0.0002324889999840707
},
"communicator.exchange": {
"total": 0.043364121999957206,
"count": 1,
"is_parallel": true,
"self": 0.043364121999957206
},
"steps_from_proto": {
"total": 0.0007629760000327224,
"count": 1,
"is_parallel": true,
"self": 0.0002173650000258931,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005456110000068293,
"count": 2,
"is_parallel": true,
"self": 0.0005456110000068293
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1275.100194562047,
"count": 231904,
"is_parallel": true,
"self": 40.009512099981066,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.62280245710167,
"count": 231904,
"is_parallel": true,
"self": 80.62280245710167
},
"communicator.exchange": {
"total": 1056.869005893022,
"count": 231904,
"is_parallel": true,
"self": 1056.869005893022
},
"steps_from_proto": {
"total": 97.59887411194217,
"count": 231904,
"is_parallel": true,
"self": 35.090612465929325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.50826164601284,
"count": 463808,
"is_parallel": true,
"self": 62.50826164601284
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 536.849436971059,
"count": 231905,
"self": 6.441595648122757,
"children": {
"process_trajectory": {
"total": 134.0760429009381,
"count": 231905,
"self": 132.58620162193859,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4898412789995064,
"count": 10,
"self": 1.4898412789995064
}
}
},
"_update_policy": {
"total": 396.33179842199814,
"count": 97,
"self": 336.7532697299947,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.57852869200343,
"count": 2910,
"self": 59.57852869200343
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5219998203974683e-06,
"count": 1,
"self": 1.5219998203974683e-06
},
"TrainerController._save_models": {
"total": 0.18520223099994837,
"count": 1,
"self": 0.0029177880001043377,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18228444299984403,
"count": 1,
"self": 0.18228444299984403
}
}
}
}
}
}
}