ppo-Huggy / run_logs /timers.json
Mullerjo's picture
Huggy
b4ad226 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045499563217163,
"min": 1.4045499563217163,
"max": 1.4288533926010132,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70006.984375,
"min": 68758.3203125,
"max": 77362.890625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 69.38450704225352,
"min": 67.559670781893,
"max": 392.7795275590551,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49263.0,
"min": 49191.0,
"max": 50102.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49974.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49974.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.515930652618408,
"min": 0.15824119746685028,
"max": 2.548189401626587,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1786.310791015625,
"min": 19.938390731811523,
"max": 1821.787109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.908317305336536,
"min": 1.8234498164956532,
"max": 4.043156803929687,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2774.9052867889404,
"min": 229.7546768784523,
"max": 2870.5490364432335,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.908317305336536,
"min": 1.8234498164956532,
"max": 4.043156803929687,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2774.9052867889404,
"min": 229.7546768784523,
"max": 2870.5490364432335,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017079899738018867,
"min": 0.013702660831040703,
"max": 0.020003689922305057,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051239699214056605,
"min": 0.027405321662081407,
"max": 0.05540038385758332,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06486994781427913,
"min": 0.021432649716734885,
"max": 0.06726107932627201,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19460984344283738,
"min": 0.04286529943346977,
"max": 0.19460984344283738,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.886698704466674e-06,
"min": 3.886698704466674e-06,
"max": 0.00029530822656392494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.166009611340002e-05,
"min": 1.166009611340002e-05,
"max": 0.0008439255186914998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129553333333334,
"min": 0.10129553333333334,
"max": 0.19843607500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038866,
"min": 0.20771885,
"max": 0.5813084999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.464711333333346e-05,
"min": 7.464711333333346e-05,
"max": 0.004921960142499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022394134000000037,
"min": 0.00022394134000000037,
"max": 0.01406729415,
"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": "1715853879",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1715856185"
},
"total": 2306.527004806,
"count": 1,
"self": 0.4414252500000657,
"children": {
"run_training.setup": {
"total": 0.052018105000001924,
"count": 1,
"self": 0.052018105000001924
},
"TrainerController.start_learning": {
"total": 2306.033561451,
"count": 1,
"self": 4.218015355961143,
"children": {
"TrainerController._reset_env": {
"total": 2.8134895119999896,
"count": 1,
"self": 2.8134895119999896
},
"TrainerController.advance": {
"total": 2298.8758824590386,
"count": 233727,
"self": 4.617597966038829,
"children": {
"env_step": {
"total": 1812.6801645469866,
"count": 233727,
"self": 1496.142103175881,
"children": {
"SubprocessEnvManager._take_step": {
"total": 313.8431251991,
"count": 233727,
"self": 15.989050845179918,
"children": {
"TorchPolicy.evaluate": {
"total": 297.85407435392005,
"count": 222932,
"self": 297.85407435392005
}
}
},
"workers": {
"total": 2.6949361720056686,
"count": 233727,
"self": 0.0,
"children": {
"worker_root": {
"total": 2299.1571848420795,
"count": 233727,
"is_parallel": true,
"self": 1093.0972497350488,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008881879999762532,
"count": 1,
"is_parallel": true,
"self": 0.00025228199996263356,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006359060000136196,
"count": 2,
"is_parallel": true,
"self": 0.0006359060000136196
}
}
},
"UnityEnvironment.step": {
"total": 0.02919076099999529,
"count": 1,
"is_parallel": true,
"self": 0.00042635599999130136,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020860500001163018,
"count": 1,
"is_parallel": true,
"self": 0.00020860500001163018
},
"communicator.exchange": {
"total": 0.027781433000029665,
"count": 1,
"is_parallel": true,
"self": 0.027781433000029665
},
"steps_from_proto": {
"total": 0.0007743669999626945,
"count": 1,
"is_parallel": true,
"self": 0.00022466699994083683,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005497000000218577,
"count": 2,
"is_parallel": true,
"self": 0.0005497000000218577
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1206.0599351070307,
"count": 233726,
"is_parallel": true,
"self": 37.78831444906882,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.82941124405431,
"count": 233726,
"is_parallel": true,
"self": 78.82941124405431
},
"communicator.exchange": {
"total": 1002.7546935568937,
"count": 233726,
"is_parallel": true,
"self": 1002.7546935568937
},
"steps_from_proto": {
"total": 86.68751585701398,
"count": 233726,
"is_parallel": true,
"self": 30.700717746073735,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.98679811094024,
"count": 467452,
"is_parallel": true,
"self": 55.98679811094024
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.5781199460132,
"count": 233727,
"self": 6.021850279965008,
"children": {
"process_trajectory": {
"total": 155.89411528004717,
"count": 233727,
"self": 154.5443115730472,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3498037069999782,
"count": 10,
"self": 1.3498037069999782
}
}
},
"_update_policy": {
"total": 319.662154386001,
"count": 97,
"self": 258.0808753609943,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.58127902500672,
"count": 2910,
"self": 61.58127902500672
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.398000222252449e-06,
"count": 1,
"self": 1.398000222252449e-06
},
"TrainerController._save_models": {
"total": 0.12617272599982243,
"count": 1,
"self": 0.0019233069997426355,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1242494190000798,
"count": 1,
"self": 0.1242494190000798
}
}
}
}
}
}
}