ppo-Huggy / run_logs /timers.json
kayvandharsee's picture
Huggy
74c19b1 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4081404209136963,
"min": 1.408067226409912,
"max": 1.4262690544128418,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70716.8125,
"min": 67798.0,
"max": 78295.984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.21182266009852,
"min": 78.50715421303657,
"max": 447.30357142857144,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49458.0,
"min": 49293.0,
"max": 50098.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999317.0,
"min": 49511.0,
"max": 1999317.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999317.0,
"min": 49511.0,
"max": 1999317.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.448531150817871,
"min": 0.07216762751340866,
"max": 2.463794708251953,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1491.155517578125,
"min": 8.01060676574707,
"max": 1525.213134765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7758338375044573,
"min": 1.8964790648168273,
"max": 4.004166896045747,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2299.4828070402145,
"min": 210.50917619466782,
"max": 2347.571501672268,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7758338375044573,
"min": 1.8964790648168273,
"max": 4.004166896045747,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2299.4828070402145,
"min": 210.50917619466782,
"max": 2347.571501672268,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018342656801946255,
"min": 0.01438928554901698,
"max": 0.01962556036226791,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05502797040583876,
"min": 0.02877857109803396,
"max": 0.05833377338324984,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06281032491889264,
"min": 0.020973576388011377,
"max": 0.06281032491889264,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18843097475667794,
"min": 0.041947152776022754,
"max": 0.18843097475667794,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.801648732816665e-06,
"min": 3.801648732816665e-06,
"max": 0.0002953819515393501,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1404946198449995e-05,
"min": 1.1404946198449995e-05,
"max": 0.0008443782185406001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126718333333333,
"min": 0.10126718333333333,
"max": 0.19846065000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30380155,
"min": 0.20768635000000008,
"max": 0.5814594000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.323244833333329e-05,
"min": 7.323244833333329e-05,
"max": 0.004923186434999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021969734499999988,
"min": 0.00021969734499999988,
"max": 0.01407482406,
"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": "1723047566",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723049899"
},
"total": 2333.726442062,
"count": 1,
"self": 0.6330627090001144,
"children": {
"run_training.setup": {
"total": 0.060312103000001116,
"count": 1,
"self": 0.060312103000001116
},
"TrainerController.start_learning": {
"total": 2333.03306725,
"count": 1,
"self": 4.256439939993925,
"children": {
"TrainerController._reset_env": {
"total": 3.1356763719999208,
"count": 1,
"self": 3.1356763719999208
},
"TrainerController.advance": {
"total": 2325.442056693006,
"count": 232568,
"self": 4.488315785044051,
"children": {
"env_step": {
"total": 1834.675133278977,
"count": 232568,
"self": 1516.5769121298586,
"children": {
"SubprocessEnvManager._take_step": {
"total": 315.38186610813136,
"count": 232568,
"self": 16.650072833181866,
"children": {
"TorchPolicy.evaluate": {
"total": 298.7317932749495,
"count": 222893,
"self": 298.7317932749495
}
}
},
"workers": {
"total": 2.7163550409869686,
"count": 232568,
"self": 0.0,
"children": {
"worker_root": {
"total": 2325.6651555270573,
"count": 232568,
"is_parallel": true,
"self": 1101.644382192113,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001003004000040164,
"count": 1,
"is_parallel": true,
"self": 0.0002737280001383624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007292759999018017,
"count": 2,
"is_parallel": true,
"self": 0.0007292759999018017
}
}
},
"UnityEnvironment.step": {
"total": 0.031138935999933892,
"count": 1,
"is_parallel": true,
"self": 0.0003730319999704079,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002172299999756433,
"count": 1,
"is_parallel": true,
"self": 0.0002172299999756433
},
"communicator.exchange": {
"total": 0.029740882000055535,
"count": 1,
"is_parallel": true,
"self": 0.029740882000055535
},
"steps_from_proto": {
"total": 0.0008077919999323058,
"count": 1,
"is_parallel": true,
"self": 0.00019754999993892852,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006102419999933772,
"count": 2,
"is_parallel": true,
"self": 0.0006102419999933772
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1224.0207733349444,
"count": 232567,
"is_parallel": true,
"self": 37.87587149493902,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.09818087899691,
"count": 232567,
"is_parallel": true,
"self": 78.09818087899691
},
"communicator.exchange": {
"total": 1019.86104514398,
"count": 232567,
"is_parallel": true,
"self": 1019.86104514398
},
"steps_from_proto": {
"total": 88.18567581702825,
"count": 232567,
"is_parallel": true,
"self": 31.023195288944862,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.16248052808339,
"count": 465134,
"is_parallel": true,
"self": 57.16248052808339
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 486.2786076289851,
"count": 232568,
"self": 6.524260717007337,
"children": {
"process_trajectory": {
"total": 154.0965065559758,
"count": 232568,
"self": 152.72242599097592,
"children": {
"RLTrainer._checkpoint": {
"total": 1.374080564999872,
"count": 10,
"self": 1.374080564999872
}
}
},
"_update_policy": {
"total": 325.657840356002,
"count": 97,
"self": 262.74393070200824,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.913909653993755,
"count": 2910,
"self": 62.913909653993755
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2420000530255493e-06,
"count": 1,
"self": 1.2420000530255493e-06
},
"TrainerController._save_models": {
"total": 0.1988930029997391,
"count": 1,
"self": 0.0027605739996943157,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1961324290000448,
"count": 1,
"self": 0.1961324290000448
}
}
}
}
}
}
}