ppo-Huggy / run_logs /timers.json
aleix8's picture
Huggy
a75a180
raw
history blame contribute delete
No virus
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4086164236068726,
"min": 1.4086164236068726,
"max": 1.4296849966049194,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69174.3359375,
"min": 67961.7890625,
"max": 77275.96875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.76209677419355,
"min": 87.75444839857651,
"max": 371.74074074074076,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49482.0,
"min": 48991.0,
"max": 50185.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999904.0,
"min": 49799.0,
"max": 1999904.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999904.0,
"min": 49799.0,
"max": 1999904.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3567698001861572,
"min": -0.010439769364893436,
"max": 2.4608490467071533,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1168.957763671875,
"min": -1.3989291191101074,
"max": 1350.821044921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.557917009077726,
"min": 1.7936319003799068,
"max": 3.888823319122611,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1764.726836502552,
"min": 240.34667465090752,
"max": 2103.9875643849373,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.557917009077726,
"min": 1.7936319003799068,
"max": 3.888823319122611,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1764.726836502552,
"min": 240.34667465090752,
"max": 2103.9875643849373,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017308741157952078,
"min": 0.01447395087121145,
"max": 0.02149684188819568,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.034617482315904155,
"min": 0.029648323487102363,
"max": 0.055988740004734916,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053546959472199285,
"min": 0.02223651899645726,
"max": 0.05884205972154935,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10709391894439857,
"min": 0.04447303799291452,
"max": 0.17652617916464805,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.1293736235750095e-06,
"min": 4.1293736235750095e-06,
"max": 0.00029531152656282495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.258747247150019e-06,
"min": 8.258747247150019e-06,
"max": 0.00084406336864555,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101376425,
"min": 0.101376425,
"max": 0.19843717500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20275285,
"min": 0.20275285,
"max": 0.5813544499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.86836075000002e-05,
"min": 7.86836075000002e-05,
"max": 0.004922015032499998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001573672150000004,
"min": 0.0001573672150000004,
"max": 0.014069587055,
"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": "1698489201",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698491729"
},
"total": 2528.098752938,
"count": 1,
"self": 0.80117335299974,
"children": {
"run_training.setup": {
"total": 0.04194537500006845,
"count": 1,
"self": 0.04194537500006845
},
"TrainerController.start_learning": {
"total": 2527.25563421,
"count": 1,
"self": 4.628635318993474,
"children": {
"TrainerController._reset_env": {
"total": 8.793085438999924,
"count": 1,
"self": 8.793085438999924
},
"TrainerController.advance": {
"total": 2513.6674518670065,
"count": 231356,
"self": 5.064860079090522,
"children": {
"env_step": {
"total": 2005.2982897529384,
"count": 231356,
"self": 1648.0586744459033,
"children": {
"SubprocessEnvManager._take_step": {
"total": 354.24187223106594,
"count": 231356,
"self": 16.70256645601603,
"children": {
"TorchPolicy.evaluate": {
"total": 337.5393057750499,
"count": 222888,
"self": 337.5393057750499
}
}
},
"workers": {
"total": 2.9977430759690833,
"count": 231356,
"self": 0.0,
"children": {
"worker_root": {
"total": 2519.28465338799,
"count": 231356,
"is_parallel": true,
"self": 1177.2781909170305,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008211870000423005,
"count": 1,
"is_parallel": true,
"self": 0.00025218199994014867,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005690050001021518,
"count": 2,
"is_parallel": true,
"self": 0.0005690050001021518
}
}
},
"UnityEnvironment.step": {
"total": 0.03661917500005529,
"count": 1,
"is_parallel": true,
"self": 0.00032519200010483473,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002274299999953655,
"count": 1,
"is_parallel": true,
"self": 0.0002274299999953655
},
"communicator.exchange": {
"total": 0.03527699500000381,
"count": 1,
"is_parallel": true,
"self": 0.03527699500000381
},
"steps_from_proto": {
"total": 0.0007895579999512847,
"count": 1,
"is_parallel": true,
"self": 0.0002444669999022153,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005450910000490694,
"count": 2,
"is_parallel": true,
"self": 0.0005450910000490694
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1342.0064624709596,
"count": 231355,
"is_parallel": true,
"self": 41.251306736076685,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.72950434890117,
"count": 231355,
"is_parallel": true,
"self": 90.72950434890117
},
"communicator.exchange": {
"total": 1116.1711532619695,
"count": 231355,
"is_parallel": true,
"self": 1116.1711532619695
},
"steps_from_proto": {
"total": 93.85449812401214,
"count": 231355,
"is_parallel": true,
"self": 35.56762595476948,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.286872169242656,
"count": 462710,
"is_parallel": true,
"self": 58.286872169242656
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.3043020349777,
"count": 231356,
"self": 6.997794725019503,
"children": {
"process_trajectory": {
"total": 156.66599915395943,
"count": 231356,
"self": 155.36172565395975,
"children": {
"RLTrainer._checkpoint": {
"total": 1.304273499999681,
"count": 10,
"self": 1.304273499999681
}
}
},
"_update_policy": {
"total": 339.64050815599876,
"count": 96,
"self": 277.36192225800096,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.2785858979978,
"count": 2880,
"self": 62.2785858979978
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4269999155658297e-06,
"count": 1,
"self": 1.4269999155658297e-06
},
"TrainerController._save_models": {
"total": 0.16646015800006353,
"count": 1,
"self": 0.0030029310000827536,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16345722699998078,
"count": 1,
"self": 0.16345722699998078
}
}
}
}
}
}
}