ppo-Huggy / run_logs /timers.json
thelfer's picture
Huggy
fc29a3d
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.402104377746582,
"min": 1.402104377746582,
"max": 1.4278171062469482,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70084.1875,
"min": 67842.3359375,
"max": 77521.9453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.54211332312404,
"min": 71.54545454545455,
"max": 390.3410852713178,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49329.0,
"min": 48794.0,
"max": 50354.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999932.0,
"min": 49907.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999932.0,
"min": 49907.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.54374098777771,
"min": 0.146201491355896,
"max": 2.54374098777771,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1661.0628662109375,
"min": 18.713790893554688,
"max": 1703.134521484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.032889851932321,
"min": 1.877717963187024,
"max": 4.032889851932321,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2633.4770733118057,
"min": 240.34789928793907,
"max": 2704.648643910885,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.032889851932321,
"min": 1.877717963187024,
"max": 4.032889851932321,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2633.4770733118057,
"min": 240.34789928793907,
"max": 2704.648643910885,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017208975344450057,
"min": 0.014049318564745287,
"max": 0.022284441020262117,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05162692603335017,
"min": 0.028098637129490574,
"max": 0.05550454499510428,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06294268440041277,
"min": 0.021268355442831913,
"max": 0.06554176316907008,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1888280532012383,
"min": 0.042536710885663825,
"max": 0.19007733464241028,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.847898717400002e-06,
"min": 3.847898717400002e-06,
"max": 0.00029534190155269997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1543696152200006e-05,
"min": 1.1543696152200006e-05,
"max": 0.000843954018682,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128260000000001,
"min": 0.10128260000000001,
"max": 0.19844729999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30384780000000006,
"min": 0.20772410000000002,
"max": 0.5813180000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.400174000000004e-05,
"min": 7.400174000000004e-05,
"max": 0.0049225202699999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022200522000000012,
"min": 0.00022200522000000012,
"max": 0.014067768200000002,
"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": "1701367537",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701370093"
},
"total": 2556.0081172640002,
"count": 1,
"self": 0.4450520560003497,
"children": {
"run_training.setup": {
"total": 0.061538696000013715,
"count": 1,
"self": 0.061538696000013715
},
"TrainerController.start_learning": {
"total": 2555.501526512,
"count": 1,
"self": 4.945091950988626,
"children": {
"TrainerController._reset_env": {
"total": 3.47770729399997,
"count": 1,
"self": 3.47770729399997
},
"TrainerController.advance": {
"total": 2546.9707991940113,
"count": 233190,
"self": 5.199669460140285,
"children": {
"env_step": {
"total": 2011.4708112989283,
"count": 233190,
"self": 1671.1438052699543,
"children": {
"SubprocessEnvManager._take_step": {
"total": 337.20173392797824,
"count": 233190,
"self": 17.29298046106163,
"children": {
"TorchPolicy.evaluate": {
"total": 319.9087534669166,
"count": 222905,
"self": 319.9087534669166
}
}
},
"workers": {
"total": 3.125272100995801,
"count": 233190,
"self": 0.0,
"children": {
"worker_root": {
"total": 2547.954732437016,
"count": 233190,
"is_parallel": true,
"self": 1188.154964815068,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008400290000167843,
"count": 1,
"is_parallel": true,
"self": 0.0002404020000312812,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005996269999855031,
"count": 2,
"is_parallel": true,
"self": 0.0005996269999855031
}
}
},
"UnityEnvironment.step": {
"total": 0.03054470400002174,
"count": 1,
"is_parallel": true,
"self": 0.00031261000003723893,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020743200002470985,
"count": 1,
"is_parallel": true,
"self": 0.00020743200002470985
},
"communicator.exchange": {
"total": 0.02930795899999339,
"count": 1,
"is_parallel": true,
"self": 0.02930795899999339
},
"steps_from_proto": {
"total": 0.000716702999966401,
"count": 1,
"is_parallel": true,
"self": 0.0001955399999360452,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005211630000303558,
"count": 2,
"is_parallel": true,
"self": 0.0005211630000303558
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1359.799767621948,
"count": 233189,
"is_parallel": true,
"self": 40.91146742302885,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.82171953593786,
"count": 233189,
"is_parallel": true,
"self": 85.82171953593786
},
"communicator.exchange": {
"total": 1139.083926253031,
"count": 233189,
"is_parallel": true,
"self": 1139.083926253031
},
"steps_from_proto": {
"total": 93.98265440995033,
"count": 233189,
"is_parallel": true,
"self": 33.1119738459214,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.87068056402893,
"count": 466378,
"is_parallel": true,
"self": 60.87068056402893
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 530.3003184349428,
"count": 233190,
"self": 7.368258570825333,
"children": {
"process_trajectory": {
"total": 165.26153314211854,
"count": 233190,
"self": 164.00407752411923,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2574556179993124,
"count": 10,
"self": 1.2574556179993124
}
}
},
"_update_policy": {
"total": 357.67052672199895,
"count": 97,
"self": 290.6762871400024,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.99423958199657,
"count": 2910,
"self": 66.99423958199657
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.020000106829684e-07,
"count": 1,
"self": 9.020000106829684e-07
},
"TrainerController._save_models": {
"total": 0.10792717100002847,
"count": 1,
"self": 0.001938924000114639,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10598824699991383,
"count": 1,
"self": 0.10598824699991383
}
}
}
}
}
}
}