ppo-Huggy / run_logs /timers.json
bob1-bob2's picture
Huggy
25fa1d4 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4003946781158447,
"min": 1.4003946781158447,
"max": 1.4274053573608398,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69584.2109375,
"min": 68650.5078125,
"max": 75544.3203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.7114337568058,
"min": 74.41478129713424,
"max": 371.4632352941176,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49431.0,
"min": 48816.0,
"max": 50519.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999922.0,
"min": 49905.0,
"max": 1999922.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999922.0,
"min": 49905.0,
"max": 1999922.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4459781646728516,
"min": 0.11074564605951309,
"max": 2.505610942840576,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1347.7340087890625,
"min": 14.950662612915039,
"max": 1615.28955078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6664950582596005,
"min": 1.7668895930051804,
"max": 3.990247367436255,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2020.23877710104,
"min": 238.53009505569935,
"max": 2593.4872354269028,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6664950582596005,
"min": 1.7668895930051804,
"max": 3.990247367436255,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2020.23877710104,
"min": 238.53009505569935,
"max": 2593.4872354269028,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017902682938276685,
"min": 0.013891674080676035,
"max": 0.01947308668200599,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05370804881483006,
"min": 0.02840780364155459,
"max": 0.058419260046017975,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05053419118954076,
"min": 0.022078538592904803,
"max": 0.06184215079993009,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15160257356862228,
"min": 0.04415707718580961,
"max": 0.17949151198069258,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.638798787099994e-06,
"min": 3.638798787099994e-06,
"max": 0.000295369726543425,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0916396361299983e-05,
"min": 1.0916396361299983e-05,
"max": 0.0008443095185635,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121290000000001,
"min": 0.10121290000000001,
"max": 0.19845657500000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30363870000000004,
"min": 0.20758265,
"max": 0.5814364999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.052370999999993e-05,
"min": 7.052370999999993e-05,
"max": 0.004922983092500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002115711299999998,
"min": 0.0002115711299999998,
"max": 0.014073681350000002,
"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": "1748918999",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748921493"
},
"total": 2493.241394683,
"count": 1,
"self": 0.48839357900033065,
"children": {
"run_training.setup": {
"total": 0.023992608999833465,
"count": 1,
"self": 0.023992608999833465
},
"TrainerController.start_learning": {
"total": 2492.729008495,
"count": 1,
"self": 4.501416689169218,
"children": {
"TrainerController._reset_env": {
"total": 3.9546242769999935,
"count": 1,
"self": 3.9546242769999935
},
"TrainerController.advance": {
"total": 2484.1614394048306,
"count": 233056,
"self": 4.744588924901564,
"children": {
"env_step": {
"total": 1981.9945865369573,
"count": 233056,
"self": 1567.6484160340526,
"children": {
"SubprocessEnvManager._take_step": {
"total": 411.55804866484914,
"count": 233056,
"self": 16.430828874799772,
"children": {
"TorchPolicy.evaluate": {
"total": 395.12721979004937,
"count": 223038,
"self": 395.12721979004937
}
}
},
"workers": {
"total": 2.788121838055531,
"count": 233056,
"self": 0.0,
"children": {
"worker_root": {
"total": 2485.1335378039525,
"count": 233056,
"is_parallel": true,
"self": 1208.9442502870425,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009896560000015597,
"count": 1,
"is_parallel": true,
"self": 0.0002723360000800312,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007173199999215285,
"count": 2,
"is_parallel": true,
"self": 0.0007173199999215285
}
}
},
"UnityEnvironment.step": {
"total": 0.0552776320000703,
"count": 1,
"is_parallel": true,
"self": 0.0003318130000025121,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001934649999384419,
"count": 1,
"is_parallel": true,
"self": 0.0001934649999384419
},
"communicator.exchange": {
"total": 0.054032372000165196,
"count": 1,
"is_parallel": true,
"self": 0.054032372000165196
},
"steps_from_proto": {
"total": 0.0007199819999641477,
"count": 1,
"is_parallel": true,
"self": 0.00018718599994826945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005327960000158782,
"count": 2,
"is_parallel": true,
"self": 0.0005327960000158782
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1276.18928751691,
"count": 233055,
"is_parallel": true,
"self": 37.54013338083314,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.61374845904447,
"count": 233055,
"is_parallel": true,
"self": 79.61374845904447
},
"communicator.exchange": {
"total": 1070.5719775620605,
"count": 233055,
"is_parallel": true,
"self": 1070.5719775620605
},
"steps_from_proto": {
"total": 88.46342811497198,
"count": 233055,
"is_parallel": true,
"self": 30.721939100818418,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.74148901415356,
"count": 466110,
"is_parallel": true,
"self": 57.74148901415356
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 497.42226394297154,
"count": 233056,
"self": 7.07655978698449,
"children": {
"process_trajectory": {
"total": 171.1555083489859,
"count": 233056,
"self": 169.9468401729855,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2086681760004012,
"count": 10,
"self": 1.2086681760004012
}
}
},
"_update_policy": {
"total": 319.19019580700115,
"count": 97,
"self": 254.26639437699987,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.92380143000128,
"count": 2910,
"self": 64.92380143000128
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.660000846954063e-07,
"count": 1,
"self": 7.660000846954063e-07
},
"TrainerController._save_models": {
"total": 0.11152735800033042,
"count": 1,
"self": 0.001557437000428763,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10996992099990166,
"count": 1,
"self": 0.10996992099990166
}
}
}
}
}
}
}