ppo-Huggy / run_logs /timers.json
EvaristeL's picture
Huggy
4a2896e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4042733907699585,
"min": 1.4042733907699585,
"max": 1.4289544820785522,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71143.296875,
"min": 68813.265625,
"max": 77202.0625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.66793893129771,
"min": 79.22347266881029,
"max": 402.9596774193548,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50130.0,
"min": 48884.0,
"max": 50199.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999912.0,
"min": 49485.0,
"max": 1999912.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999912.0,
"min": 49485.0,
"max": 1999912.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.441033124923706,
"min": 0.12501153349876404,
"max": 2.478972911834717,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1279.101318359375,
"min": 15.376418113708496,
"max": 1541.921142578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.730451064710399,
"min": 1.6803047480137367,
"max": 3.975518060710005,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1954.756357908249,
"min": 206.67748400568962,
"max": 2470.9234322309494,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.730451064710399,
"min": 1.6803047480137367,
"max": 3.975518060710005,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1954.756357908249,
"min": 206.67748400568962,
"max": 2470.9234322309494,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017220379777750674,
"min": 0.012208154527979787,
"max": 0.02348933043152404,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05166113933325202,
"min": 0.024416309055959574,
"max": 0.05805646203455884,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05006351259847482,
"min": 0.02114484856526057,
"max": 0.06952700161685546,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15019053779542446,
"min": 0.04228969713052114,
"max": 0.19714925785859425,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.525848824750006e-06,
"min": 3.525848824750006e-06,
"max": 0.00029536612654462496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0577546474250018e-05,
"min": 1.0577546474250018e-05,
"max": 0.0008443699685433501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117525000000004,
"min": 0.10117525000000004,
"max": 0.198455375,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035257500000001,
"min": 0.20753319999999997,
"max": 0.58145665,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.864497500000008e-05,
"min": 6.864497500000008e-05,
"max": 0.004922923212499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020593492500000024,
"min": 0.00020593492500000024,
"max": 0.014074686835000001,
"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": "1741863389",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --force --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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1741865584"
},
"total": 2195.2730825880003,
"count": 1,
"self": 0.3214478500003679,
"children": {
"run_training.setup": {
"total": 0.08482109499982471,
"count": 1,
"self": 0.08482109499982471
},
"TrainerController.start_learning": {
"total": 2194.866813643,
"count": 1,
"self": 4.399893302095279,
"children": {
"TrainerController._reset_env": {
"total": 3.2583202320001874,
"count": 1,
"self": 3.2583202320001874
},
"TrainerController.advance": {
"total": 2187.092569417905,
"count": 232625,
"self": 4.4394521478620845,
"children": {
"env_step": {
"total": 1738.6640368839771,
"count": 232625,
"self": 1340.6366999391971,
"children": {
"SubprocessEnvManager._take_step": {
"total": 395.29978841491265,
"count": 232625,
"self": 15.448615598901142,
"children": {
"TorchPolicy.evaluate": {
"total": 379.8511728160115,
"count": 223058,
"self": 379.8511728160115
}
}
},
"workers": {
"total": 2.727548529867363,
"count": 232625,
"self": 0.0,
"children": {
"worker_root": {
"total": 2187.0410029550685,
"count": 232625,
"is_parallel": true,
"self": 1113.67548606103,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010340339999856951,
"count": 1,
"is_parallel": true,
"self": 0.000250922000304854,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007831119996808411,
"count": 2,
"is_parallel": true,
"self": 0.0007831119996808411
}
}
},
"UnityEnvironment.step": {
"total": 0.02245922599968253,
"count": 1,
"is_parallel": true,
"self": 0.00041419299986955593,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002125430000887718,
"count": 1,
"is_parallel": true,
"self": 0.0002125430000887718
},
"communicator.exchange": {
"total": 0.020992611000110628,
"count": 1,
"is_parallel": true,
"self": 0.020992611000110628
},
"steps_from_proto": {
"total": 0.0008398789996135747,
"count": 1,
"is_parallel": true,
"self": 0.00022068199950808776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000619197000105487,
"count": 2,
"is_parallel": true,
"self": 0.000619197000105487
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1073.3655168940386,
"count": 232624,
"is_parallel": true,
"self": 32.049521148760505,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 64.77416333422889,
"count": 232624,
"is_parallel": true,
"self": 64.77416333422889
},
"communicator.exchange": {
"total": 901.8672659069753,
"count": 232624,
"is_parallel": true,
"self": 901.8672659069753
},
"steps_from_proto": {
"total": 74.67456650407394,
"count": 232624,
"is_parallel": true,
"self": 28.11475881843944,
"children": {
"_process_rank_one_or_two_observation": {
"total": 46.559807685634496,
"count": 465248,
"is_parallel": true,
"self": 46.559807685634496
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 443.9890803860658,
"count": 232625,
"self": 6.4499611549517795,
"children": {
"process_trajectory": {
"total": 158.83462800611687,
"count": 232625,
"self": 157.50843389711736,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3261941089995162,
"count": 10,
"self": 1.3261941089995162
}
}
},
"_update_policy": {
"total": 278.7044912249971,
"count": 97,
"self": 226.28334269198922,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.42114853300791,
"count": 2910,
"self": 52.42114853300791
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.049999789567664e-07,
"count": 1,
"self": 9.049999789567664e-07
},
"TrainerController._save_models": {
"total": 0.11602978599967173,
"count": 1,
"self": 0.00298527299946727,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11304451300020446,
"count": 1,
"self": 0.11304451300020446
}
}
}
}
}
}
}