ppo-Pyramids123 / run_logs /timers.json
MY11111111's picture
First training of Pyramids
3dfa5a1 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7599734663963318,
"min": 0.7209876179695129,
"max": 1.4070985317230225,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 22993.7578125,
"min": 21641.1640625,
"max": 42685.7421875,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479905.0,
"min": 29952.0,
"max": 479905.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479905.0,
"min": 29952.0,
"max": 479905.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.01879260689020157,
"min": -0.10406187176704407,
"max": 0.2354099154472351,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 4.622981071472168,
"min": -25.07891082763672,
"max": 55.79214859008789,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.033645398914813995,
"min": 0.025427494198083878,
"max": 0.415382444858551,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.27676773071289,
"min": 6.1788811683654785,
"max": 98.44564056396484,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06733978535977894,
"min": 0.06575865745959983,
"max": 0.07418710289688644,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.010096780396684,
"min": 0.47318129119815855,
"max": 1.010096780396684,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.005578834796633482,
"min": 0.0001478741731252948,
"max": 0.007087473844843657,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.08368252194950222,
"min": 0.0016266159043782427,
"max": 0.09486772501394643,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.102853299052e-05,
"min": 2.102853299052e-05,
"max": 0.00029030126037577137,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0003154279948578,
"min": 0.0003154279948578,
"max": 0.0024124490958503998,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10700948,
"min": 0.10700948,
"max": 0.19676708571428575,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.6051422,
"min": 1.3382272,
"max": 2.09259,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007102470520000002,
"min": 0.0007102470520000002,
"max": 0.00967703186285714,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.010653705780000003,
"min": 0.010653705780000003,
"max": 0.08044454504,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.026969928294420242,
"min": 0.026969928294420242,
"max": 0.4718073904514313,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.40454891324043274,
"min": 0.3871544897556305,
"max": 3.3026516437530518,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 837.6666666666666,
"min": 831.3714285714286,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30156.0,
"min": 15984.0,
"max": 31968.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.06025004221333398,
"min": -1.0000000521540642,
"max": 0.025474242653165544,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -2.169001519680023,
"min": -32.000001668930054,
"max": 0.8915984928607941,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.06025004221333398,
"min": -1.0000000521540642,
"max": 0.025474242653165544,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -2.169001519680023,
"min": -32.000001668930054,
"max": 0.8915984928607941,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.23489424048845345,
"min": 0.23489424048845345,
"max": 9.061561428010464,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 8.456192657584324,
"min": 7.9692321280017495,
"max": 144.98498284816742,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1714212100",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714213936"
},
"total": 1835.846905264,
"count": 1,
"self": 0.8496744670001135,
"children": {
"run_training.setup": {
"total": 0.08212086200001067,
"count": 1,
"self": 0.08212086200001067
},
"TrainerController.start_learning": {
"total": 1834.915109935,
"count": 1,
"self": 1.3568495619740588,
"children": {
"TrainerController._reset_env": {
"total": 4.251138632999982,
"count": 1,
"self": 4.251138632999982
},
"TrainerController.advance": {
"total": 1829.1851239430255,
"count": 31520,
"self": 1.5376524270322989,
"children": {
"env_step": {
"total": 1203.8001412769786,
"count": 31520,
"self": 1104.5481686250305,
"children": {
"SubprocessEnvManager._take_step": {
"total": 98.34488847899775,
"count": 31520,
"self": 4.651149765976925,
"children": {
"TorchPolicy.evaluate": {
"total": 93.69373871302082,
"count": 31321,
"self": 93.69373871302082
}
}
},
"workers": {
"total": 0.9070841729503627,
"count": 31520,
"self": 0.0,
"children": {
"worker_root": {
"total": 1830.2551806290148,
"count": 31520,
"is_parallel": true,
"self": 846.5177497510476,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008484212999974261,
"count": 1,
"is_parallel": true,
"self": 0.005564789999880304,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002919423000093957,
"count": 8,
"is_parallel": true,
"self": 0.002919423000093957
}
}
},
"UnityEnvironment.step": {
"total": 0.08026218899999549,
"count": 1,
"is_parallel": true,
"self": 0.0009926469999754772,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007841110000299523,
"count": 1,
"is_parallel": true,
"self": 0.0007841110000299523
},
"communicator.exchange": {
"total": 0.07452836900006332,
"count": 1,
"is_parallel": true,
"self": 0.07452836900006332
},
"steps_from_proto": {
"total": 0.0039570619999267365,
"count": 1,
"is_parallel": true,
"self": 0.0006147659996713628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0033422960002553737,
"count": 8,
"is_parallel": true,
"self": 0.0033422960002553737
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 983.7374308779672,
"count": 31519,
"is_parallel": true,
"self": 31.030970321985478,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 17.714325252019307,
"count": 31519,
"is_parallel": true,
"self": 17.714325252019307
},
"communicator.exchange": {
"total": 859.7539580449691,
"count": 31519,
"is_parallel": true,
"self": 859.7539580449691
},
"steps_from_proto": {
"total": 75.23817725899335,
"count": 31519,
"is_parallel": true,
"self": 16.938205290088035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.29997196890531,
"count": 252152,
"is_parallel": true,
"self": 58.29997196890531
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 623.8473302390146,
"count": 31520,
"self": 2.549967814034062,
"children": {
"process_trajectory": {
"total": 98.67590811597938,
"count": 31520,
"self": 98.49947127997939,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1764368359999935,
"count": 1,
"self": 0.1764368359999935
}
}
},
"_update_policy": {
"total": 522.6214543090011,
"count": 199,
"self": 210.35886820299856,
"children": {
"TorchPPOOptimizer.update": {
"total": 312.2625861060026,
"count": 11460,
"self": 312.2625861060026
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5830000847927295e-06,
"count": 1,
"self": 1.5830000847927295e-06
},
"TrainerController._save_models": {
"total": 0.12199621400031901,
"count": 1,
"self": 0.005445809000320878,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11655040499999814,
"count": 1,
"self": 0.11655040499999814
}
}
}
}
}
}
}