ppo-Huggy / run_logs /timers.json
nabeelraza's picture
Huggy
0a6a8b2
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407058835029602,
"min": 1.407058835029602,
"max": 1.4287517070770264,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70248.8203125,
"min": 68487.6640625,
"max": 76303.4609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.87840290381125,
"min": 82.78894472361809,
"max": 413.8688524590164,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49523.0,
"min": 48942.0,
"max": 50492.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999988.0,
"min": 49865.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999988.0,
"min": 49865.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4474406242370605,
"min": 0.19212594628334045,
"max": 2.4474406242370605,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1348.539794921875,
"min": 23.24724006652832,
"max": 1413.7386474609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8331823055843692,
"min": 1.7519642506256576,
"max": 3.898274413791084,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2112.0834503769875,
"min": 211.98767432570457,
"max": 2202.3407073020935,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8331823055843692,
"min": 1.7519642506256576,
"max": 3.898274413791084,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2112.0834503769875,
"min": 211.98767432570457,
"max": 2202.3407073020935,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014980527065603787,
"min": 0.012310905501282022,
"max": 0.020588816523862383,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04494158119681136,
"min": 0.02777955311127395,
"max": 0.05783195444795031,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050936323197351564,
"min": 0.02035594806075096,
"max": 0.05658355560153723,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1528089695920547,
"min": 0.04071189612150192,
"max": 0.1624954373886188,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3164988945333296e-06,
"min": 3.3164988945333296e-06,
"max": 0.000295256026581325,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.949496683599989e-06,
"min": 9.949496683599989e-06,
"max": 0.00084366826877725,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110546666666666,
"min": 0.10110546666666666,
"max": 0.19841867500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033164,
"min": 0.20734750000000002,
"max": 0.5812227500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.51627866666666e-05,
"min": 6.51627866666666e-05,
"max": 0.004921091882499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019548835999999982,
"min": 0.00019548835999999982,
"max": 0.014063015225000003,
"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": "1683720484",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "1683723362"
},
"total": 2878.1733393580002,
"count": 1,
"self": 0.4409844169999815,
"children": {
"run_training.setup": {
"total": 0.045161254000049667,
"count": 1,
"self": 0.045161254000049667
},
"TrainerController.start_learning": {
"total": 2877.687193687,
"count": 1,
"self": 5.8104586191234375,
"children": {
"TrainerController._reset_env": {
"total": 4.221501566000029,
"count": 1,
"self": 4.221501566000029
},
"TrainerController.advance": {
"total": 2867.520719684877,
"count": 232129,
"self": 5.511534984966602,
"children": {
"env_step": {
"total": 2250.4195606419535,
"count": 232129,
"self": 1903.7159454979403,
"children": {
"SubprocessEnvManager._take_step": {
"total": 343.10096555695156,
"count": 232129,
"self": 20.297670868839532,
"children": {
"TorchPolicy.evaluate": {
"total": 322.80329468811203,
"count": 222987,
"self": 322.80329468811203
}
}
},
"workers": {
"total": 3.6026495870615918,
"count": 232129,
"self": 0.0,
"children": {
"worker_root": {
"total": 2868.1391763350557,
"count": 232129,
"is_parallel": true,
"self": 1317.7989176120304,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010002559999975347,
"count": 1,
"is_parallel": true,
"self": 0.00031417100001362996,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006860849999839047,
"count": 2,
"is_parallel": true,
"self": 0.0006860849999839047
}
}
},
"UnityEnvironment.step": {
"total": 0.0879054829999859,
"count": 1,
"is_parallel": true,
"self": 0.0003865710001491607,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022262599998157384,
"count": 1,
"is_parallel": true,
"self": 0.00022262599998157384
},
"communicator.exchange": {
"total": 0.08650281299992457,
"count": 1,
"is_parallel": true,
"self": 0.08650281299992457
},
"steps_from_proto": {
"total": 0.0007934729999306,
"count": 1,
"is_parallel": true,
"self": 0.00024779900002158683,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005456739999090132,
"count": 2,
"is_parallel": true,
"self": 0.0005456739999090132
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1550.3402587230253,
"count": 232128,
"is_parallel": true,
"self": 44.73328526273872,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 94.10888196006965,
"count": 232128,
"is_parallel": true,
"self": 94.10888196006965
},
"communicator.exchange": {
"total": 1300.9747184591051,
"count": 232128,
"is_parallel": true,
"self": 1300.9747184591051
},
"steps_from_proto": {
"total": 110.523373041112,
"count": 232128,
"is_parallel": true,
"self": 42.30954282710775,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.21383021400425,
"count": 464256,
"is_parallel": true,
"self": 68.21383021400425
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 611.5896240579568,
"count": 232129,
"self": 8.340529647978201,
"children": {
"process_trajectory": {
"total": 156.9337412969811,
"count": 232129,
"self": 155.47453535098077,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4592059460003384,
"count": 10,
"self": 1.4592059460003384
}
}
},
"_update_policy": {
"total": 446.3153531129975,
"count": 97,
"self": 381.3935664910126,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.9217866219849,
"count": 2910,
"self": 64.9217866219849
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0779999684018549e-06,
"count": 1,
"self": 1.0779999684018549e-06
},
"TrainerController._save_models": {
"total": 0.1345127390000016,
"count": 1,
"self": 0.002938518000064505,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1315742209999371,
"count": 1,
"self": 0.1315742209999371
}
}
}
}
}
}
}