ppo-Huggy / run_logs /timers.json
Hikari710's picture
Huggy
7290774 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3845856189727783,
"min": 1.3845856189727783,
"max": 1.428048014640808,
"count": 60
},
"Huggy.Policy.Entropy.sum": {
"value": 69610.0390625,
"min": 67910.2265625,
"max": 76948.578125,
"count": 60
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.2247191011236,
"min": 72.52058823529411,
"max": 413.6198347107438,
"count": 60
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49357.0,
"min": 48795.0,
"max": 50048.0,
"count": 60
},
"Huggy.Step.mean": {
"value": 2999960.0,
"min": 49749.0,
"max": 2999960.0,
"count": 60
},
"Huggy.Step.sum": {
"value": 2999960.0,
"min": 49749.0,
"max": 2999960.0,
"count": 60
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.542083501815796,
"min": 0.0828901007771492,
"max": 2.552384614944458,
"count": 60
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1583.718017578125,
"min": 9.94681167602539,
"max": 1665.2705078125,
"count": 60
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.887510859803633,
"min": 1.7501572526991367,
"max": 4.017692889292519,
"count": 60
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2421.9192656576633,
"min": 210.0188703238964,
"max": 2531.380338549614,
"count": 60
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.887510859803633,
"min": 1.7501572526991367,
"max": 4.017692889292519,
"count": 60
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2421.9192656576633,
"min": 210.0188703238964,
"max": 2531.380338549614,
"count": 60
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01660794256895315,
"min": 0.01399339454061798,
"max": 0.020888691977840306,
"count": 60
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0332158851379063,
"min": 0.02798678908123596,
"max": 0.058584109460934994,
"count": 60
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05082200939456622,
"min": 0.021174810174852607,
"max": 0.06400912838677565,
"count": 60
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10164401878913244,
"min": 0.042349620349705214,
"max": 0.17585579901933668,
"count": 60
},
"Huggy.Policy.LearningRate.mean": {
"value": 2.304249231950011e-06,
"min": 2.304249231950011e-06,
"max": 0.0002968983510338833,
"count": 60
},
"Huggy.Policy.LearningRate.sum": {
"value": 4.608498463900022e-06,
"min": 4.608498463900022e-06,
"max": 0.0008626778124407332,
"count": 60
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10076805000000003,
"min": 0.10076805000000003,
"max": 0.19896611666666664,
"count": 60
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20153610000000005,
"min": 0.20153610000000005,
"max": 0.5875592666666666,
"count": 60
},
"Huggy.Policy.Beta.mean": {
"value": 4.832569500000017e-05,
"min": 4.832569500000017e-05,
"max": 0.0049484092216666685,
"count": 60
},
"Huggy.Policy.Beta.sum": {
"value": 9.665139000000035e-05,
"min": 9.665139000000035e-05,
"max": 0.014379207406666664,
"count": 60
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 60
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1728108405",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728112199"
},
"total": 3794.0766458319995,
"count": 1,
"self": 0.7791622069998994,
"children": {
"run_training.setup": {
"total": 0.05956946000003427,
"count": 1,
"self": 0.05956946000003427
},
"TrainerController.start_learning": {
"total": 3793.2379141649994,
"count": 1,
"self": 6.673267492006289,
"children": {
"TrainerController._reset_env": {
"total": 2.383786158000021,
"count": 1,
"self": 2.383786158000021
},
"TrainerController.advance": {
"total": 3783.9922555739927,
"count": 350462,
"self": 7.200376398207027,
"children": {
"env_step": {
"total": 3007.3924654618704,
"count": 350462,
"self": 2377.2610067368933,
"children": {
"SubprocessEnvManager._take_step": {
"total": 625.8144166889888,
"count": 350462,
"self": 24.382451260995254,
"children": {
"TorchPolicy.evaluate": {
"total": 601.4319654279935,
"count": 334442,
"self": 601.4319654279935
}
}
},
"workers": {
"total": 4.317042035988209,
"count": 350462,
"self": 0.0,
"children": {
"worker_root": {
"total": 3782.111027447937,
"count": 350462,
"is_parallel": true,
"self": 1856.5372601908175,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008714390000363892,
"count": 1,
"is_parallel": true,
"self": 0.00023835600001120838,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006330830000251808,
"count": 2,
"is_parallel": true,
"self": 0.0006330830000251808
}
}
},
"UnityEnvironment.step": {
"total": 0.029234201999997822,
"count": 1,
"is_parallel": true,
"self": 0.00036523500000384956,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021043499998540938,
"count": 1,
"is_parallel": true,
"self": 0.00021043499998540938
},
"communicator.exchange": {
"total": 0.027907045999995717,
"count": 1,
"is_parallel": true,
"self": 0.027907045999995717
},
"steps_from_proto": {
"total": 0.0007514860000128465,
"count": 1,
"is_parallel": true,
"self": 0.000212189000080798,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005392969999320485,
"count": 2,
"is_parallel": true,
"self": 0.0005392969999320485
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1925.5737672571195,
"count": 350461,
"is_parallel": true,
"self": 57.392263339047986,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 126.07094414106314,
"count": 350461,
"is_parallel": true,
"self": 126.07094414106314
},
"communicator.exchange": {
"total": 1604.9432784078967,
"count": 350461,
"is_parallel": true,
"self": 1604.9432784078967
},
"steps_from_proto": {
"total": 137.16728136911166,
"count": 350461,
"is_parallel": true,
"self": 52.13041115907936,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.0368702100323,
"count": 700922,
"is_parallel": true,
"self": 85.0368702100323
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 769.3994137139152,
"count": 350462,
"self": 9.877984934937786,
"children": {
"process_trajectory": {
"total": 259.34550563697536,
"count": 350462,
"self": 257.31570569797503,
"children": {
"RLTrainer._checkpoint": {
"total": 2.029799939000327,
"count": 15,
"self": 2.029799939000327
}
}
},
"_update_policy": {
"total": 500.17592314200203,
"count": 145,
"self": 401.24359107700604,
"children": {
"TorchPPOOptimizer.update": {
"total": 98.93233206499599,
"count": 4350,
"self": 98.93233206499599
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.503000021330081e-06,
"count": 1,
"self": 1.503000021330081e-06
},
"TrainerController._save_models": {
"total": 0.18860343800042756,
"count": 1,
"self": 0.0033927440008483245,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18521069399957923,
"count": 1,
"self": 0.18521069399957923
}
}
}
}
}
}
}