ppo-Huggy / run_logs /timers.json
AmirH98's picture
Huggy
3adf893 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4014229774475098,
"min": 1.4014229774475098,
"max": 1.4285799264907837,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70683.5703125,
"min": 69000.90625,
"max": 76331.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.71255060728745,
"min": 71.80931586608442,
"max": 420.9579831932773,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49258.0,
"min": 48736.0,
"max": 50094.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999987.0,
"min": 49464.0,
"max": 1999987.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999987.0,
"min": 49464.0,
"max": 1999987.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3912577629089355,
"min": 0.12025686353445053,
"max": 2.527874231338501,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1181.2813720703125,
"min": 14.190309524536133,
"max": 1664.3446044921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.587110243345562,
"min": 1.7961423972905692,
"max": 4.029495637657894,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1772.0324602127075,
"min": 211.94480288028717,
"max": 2576.9202803969383,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.587110243345562,
"min": 1.7961423972905692,
"max": 4.029495637657894,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1772.0324602127075,
"min": 211.94480288028717,
"max": 2576.9202803969383,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017997069749981165,
"min": 0.013267452747257066,
"max": 0.0206643745128531,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.053991209249943495,
"min": 0.029041993656816582,
"max": 0.05760941084008664,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04714368612815937,
"min": 0.020320373804618916,
"max": 0.060286453490455943,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14143105838447811,
"min": 0.04064074760923783,
"max": 0.17396786597867808,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.786798737766677e-06,
"min": 3.786798737766677e-06,
"max": 0.0002953162515612499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1360396213300031e-05,
"min": 1.1360396213300031e-05,
"max": 0.0008442198185933999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126223333333334,
"min": 0.10126223333333334,
"max": 0.19843874999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037867,
"min": 0.2076571,
"max": 0.5814066000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.298544333333351e-05,
"min": 7.298544333333351e-05,
"max": 0.0049220936249999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021895633000000052,
"min": 0.00021895633000000052,
"max": 0.01407218934,
"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": "1745621796",
"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": "1745624290"
},
"total": 2493.726204046,
"count": 1,
"self": 0.4354632650001804,
"children": {
"run_training.setup": {
"total": 0.02608277699982864,
"count": 1,
"self": 0.02608277699982864
},
"TrainerController.start_learning": {
"total": 2493.264658004,
"count": 1,
"self": 4.316735860053086,
"children": {
"TrainerController._reset_env": {
"total": 3.431218233999971,
"count": 1,
"self": 3.431218233999971
},
"TrainerController.advance": {
"total": 2485.396767717947,
"count": 233491,
"self": 4.630486571864822,
"children": {
"env_step": {
"total": 1987.8454791350375,
"count": 233491,
"self": 1566.3881127311097,
"children": {
"SubprocessEnvManager._take_step": {
"total": 418.80421843197064,
"count": 233491,
"self": 15.943493013053285,
"children": {
"TorchPolicy.evaluate": {
"total": 402.86072541891735,
"count": 223164,
"self": 402.86072541891735
}
}
},
"workers": {
"total": 2.653147971957196,
"count": 233491,
"self": 0.0,
"children": {
"worker_root": {
"total": 2485.8594398589275,
"count": 233491,
"is_parallel": true,
"self": 1206.3500233229213,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009017770000809833,
"count": 1,
"is_parallel": true,
"self": 0.00024652000024616427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000655256999834819,
"count": 2,
"is_parallel": true,
"self": 0.000655256999834819
}
}
},
"UnityEnvironment.step": {
"total": 0.030049501999883432,
"count": 1,
"is_parallel": true,
"self": 0.0002834809999967547,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021455299997796828,
"count": 1,
"is_parallel": true,
"self": 0.00021455299997796828
},
"communicator.exchange": {
"total": 0.0287195639998572,
"count": 1,
"is_parallel": true,
"self": 0.0287195639998572
},
"steps_from_proto": {
"total": 0.0008319040000515088,
"count": 1,
"is_parallel": true,
"self": 0.00018656399993233208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006453400001191767,
"count": 2,
"is_parallel": true,
"self": 0.0006453400001191767
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1279.5094165360063,
"count": 233490,
"is_parallel": true,
"self": 38.08507053594667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.5086925120288,
"count": 233490,
"is_parallel": true,
"self": 82.5086925120288
},
"communicator.exchange": {
"total": 1069.5630134040196,
"count": 233490,
"is_parallel": true,
"self": 1069.5630134040196
},
"steps_from_proto": {
"total": 89.35264008401123,
"count": 233490,
"is_parallel": true,
"self": 31.770928461930225,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.581711622081,
"count": 466980,
"is_parallel": true,
"self": 57.581711622081
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 492.92080201104454,
"count": 233491,
"self": 6.33191677104287,
"children": {
"process_trajectory": {
"total": 172.9609711930018,
"count": 233491,
"self": 171.64752047500224,
"children": {
"RLTrainer._checkpoint": {
"total": 1.313450717999558,
"count": 10,
"self": 1.313450717999558
}
}
},
"_update_policy": {
"total": 313.6279140469999,
"count": 97,
"self": 249.0352184490048,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.59269559799509,
"count": 2910,
"self": 64.59269559799509
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2549999155453406e-06,
"count": 1,
"self": 1.2549999155453406e-06
},
"TrainerController._save_models": {
"total": 0.11993493699992541,
"count": 1,
"self": 0.0015499279998039128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1183850090001215,
"count": 1,
"self": 0.1183850090001215
}
}
}
}
}
}
}