ppo-Huggy / run_logs /timers.json
carpit680's picture
Huggy
6241e18 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.411648154258728,
"min": 1.4116432666778564,
"max": 1.42985200881958,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69755.1796875,
"min": 69533.859375,
"max": 77426.5546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.89108910891089,
"min": 91.08839779005525,
"max": 420.4957983193277,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49435.0,
"min": 48879.0,
"max": 50200.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999974.0,
"min": 49493.0,
"max": 1999974.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999974.0,
"min": 49493.0,
"max": 1999974.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.397542715072632,
"min": 0.006492596585303545,
"max": 2.4292869567871094,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1210.759033203125,
"min": 0.7661263942718506,
"max": 1269.04248046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6439672140791863,
"min": 1.7872191412469087,
"max": 3.8813481752295047,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1840.2034431099892,
"min": 210.89185866713524,
"max": 2018.6895549297333,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6439672140791863,
"min": 1.7872191412469087,
"max": 3.8813481752295047,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1840.2034431099892,
"min": 210.89185866713524,
"max": 2018.6895549297333,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013557504130585585,
"min": 0.013243442521100709,
"max": 0.021439670111673574,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.02711500826117117,
"min": 0.026486885042201418,
"max": 0.05526575340384928,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05202531299243371,
"min": 0.023341924821337064,
"max": 0.062298749635616935,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10405062598486742,
"min": 0.04668384964267413,
"max": 0.1868962489068508,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.432673522474988e-06,
"min": 4.432673522474988e-06,
"max": 0.0002953017015660999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.865347044949977e-06,
"min": 8.865347044949977e-06,
"max": 0.0008437398187534,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10147752500000004,
"min": 0.10147752500000004,
"max": 0.1984339,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20295505000000008,
"min": 0.20295505000000008,
"max": 0.5812466000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.372849749999984e-05,
"min": 8.372849749999984e-05,
"max": 0.00492185161,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016745699499999967,
"min": 0.00016745699499999967,
"max": 0.01406420534,
"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": "1717042964",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717045533"
},
"total": 2568.846363762,
"count": 1,
"self": 0.44054013799950553,
"children": {
"run_training.setup": {
"total": 0.06009240499997759,
"count": 1,
"self": 0.06009240499997759
},
"TrainerController.start_learning": {
"total": 2568.3457312190003,
"count": 1,
"self": 5.265786971065154,
"children": {
"TrainerController._reset_env": {
"total": 3.2156033569999636,
"count": 1,
"self": 3.2156033569999636
},
"TrainerController.advance": {
"total": 2559.7450953099356,
"count": 231347,
"self": 5.043097520884203,
"children": {
"env_step": {
"total": 2039.5608169649793,
"count": 231347,
"self": 1680.0540831469125,
"children": {
"SubprocessEnvManager._take_step": {
"total": 356.3303284160161,
"count": 231347,
"self": 17.903671404155148,
"children": {
"TorchPolicy.evaluate": {
"total": 338.4266570118609,
"count": 222910,
"self": 338.4266570118609
}
}
},
"workers": {
"total": 3.1764054020507047,
"count": 231347,
"self": 0.0,
"children": {
"worker_root": {
"total": 2560.670814399018,
"count": 231347,
"is_parallel": true,
"self": 1212.7059438740705,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009702180000203953,
"count": 1,
"is_parallel": true,
"self": 0.0002466210000875435,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007235969999328518,
"count": 2,
"is_parallel": true,
"self": 0.0007235969999328518
}
}
},
"UnityEnvironment.step": {
"total": 0.031576344999848516,
"count": 1,
"is_parallel": true,
"self": 0.0004269469998234854,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021675499988305091,
"count": 1,
"is_parallel": true,
"self": 0.00021675499988305091
},
"communicator.exchange": {
"total": 0.030090900000004694,
"count": 1,
"is_parallel": true,
"self": 0.030090900000004694
},
"steps_from_proto": {
"total": 0.000841743000137285,
"count": 1,
"is_parallel": true,
"self": 0.0002269950000481913,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006147480000890937,
"count": 2,
"is_parallel": true,
"self": 0.0006147480000890937
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1347.9648705249476,
"count": 231346,
"is_parallel": true,
"self": 41.16855541792984,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.44938876501351,
"count": 231346,
"is_parallel": true,
"self": 82.44938876501351
},
"communicator.exchange": {
"total": 1128.5906703289706,
"count": 231346,
"is_parallel": true,
"self": 1128.5906703289706
},
"steps_from_proto": {
"total": 95.75625601303364,
"count": 231346,
"is_parallel": true,
"self": 33.80812813895113,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.9481278740825,
"count": 462692,
"is_parallel": true,
"self": 61.9481278740825
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 515.1411808240719,
"count": 231347,
"self": 7.747920293121524,
"children": {
"process_trajectory": {
"total": 159.227875483949,
"count": 231347,
"self": 157.741620717949,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4862547660000018,
"count": 10,
"self": 1.4862547660000018
}
}
},
"_update_policy": {
"total": 348.16538504700134,
"count": 96,
"self": 281.3610938629947,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.80429118400662,
"count": 2880,
"self": 66.80429118400662
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0139997357327957e-06,
"count": 1,
"self": 1.0139997357327957e-06
},
"TrainerController._save_models": {
"total": 0.11924456699989605,
"count": 1,
"self": 0.0018644369997673493,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1173801300001287,
"count": 1,
"self": 0.1173801300001287
}
}
}
}
}
}
}