Weiming1122's picture
First Push
9f595c7
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5720550417900085,
"min": 0.5720550417900085,
"max": 1.399213433265686,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17225.720703125,
"min": 17225.720703125,
"max": 42446.5390625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989931.0,
"min": 29952.0,
"max": 989931.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989931.0,
"min": 29952.0,
"max": 989931.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.2123047113418579,
"min": -0.10842642188072205,
"max": 0.2342093139886856,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 53.50078582763672,
"min": -26.130767822265625,
"max": 59.489166259765625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.014287954196333885,
"min": -0.014287954196333885,
"max": 0.49244895577430725,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -3.600564479827881,
"min": -3.600564479827881,
"max": 118.18775177001953,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06848910263908606,
"min": 0.0664178491161216,
"max": 0.07404041190594221,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9588474369472048,
"min": 0.5050818934543566,
"max": 1.0401366942581567,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.007426097913897441,
"min": 0.0006640134410438616,
"max": 0.013296655008353067,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.10396537079456417,
"min": 0.0086321747335702,
"max": 0.12501343971662743,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.581826044185715e-06,
"min": 7.581826044185715e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010614556461860001,
"min": 0.00010614556461860001,
"max": 0.0033730243756586002,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252724285714288,
"min": 0.10252724285714288,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353814000000003,
"min": 1.3886848,
"max": 2.4427451000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002624715614285715,
"min": 0.0002624715614285715,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036746018600000013,
"min": 0.0036746018600000013,
"max": 0.11245170586000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.016102595254778862,
"min": 0.01606728695333004,
"max": 0.6395440697669983,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.22543634474277496,
"min": 0.22494202852249146,
"max": 4.476808547973633,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 656.6170212765958,
"min": 645.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30861.0,
"min": 15984.0,
"max": 33839.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.7198499697260559,
"min": -1.0000000521540642,
"max": 0.8330912726080936,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 34.55279854685068,
"min": -30.738001748919487,
"max": 38.322198539972305,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.7198499697260559,
"min": -1.0000000521540642,
"max": 0.8330912726080936,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 34.55279854685068,
"min": -30.738001748919487,
"max": 38.322198539972305,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.10987398233252559,
"min": 0.1085434852461533,
"max": 12.663976205512881,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.273951151961228,
"min": 4.989702765644324,
"max": 202.6236192882061,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1703749360",
"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=PyramidsRNDTraining1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703751505"
},
"total": 2144.8327315800007,
"count": 1,
"self": 0.5279598940005599,
"children": {
"run_training.setup": {
"total": 0.051945307000096363,
"count": 1,
"self": 0.051945307000096363
},
"TrainerController.start_learning": {
"total": 2144.252826379,
"count": 1,
"self": 1.385937461888716,
"children": {
"TrainerController._reset_env": {
"total": 2.105323063000469,
"count": 1,
"self": 2.105323063000469
},
"TrainerController.advance": {
"total": 2140.6726628761116,
"count": 63303,
"self": 1.4413517019211213,
"children": {
"env_step": {
"total": 1489.9902311011647,
"count": 63303,
"self": 1358.2981759391823,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.84719502003463,
"count": 63303,
"self": 4.7383241800762335,
"children": {
"TorchPolicy.evaluate": {
"total": 126.1088708399584,
"count": 62551,
"self": 126.1088708399584
}
}
},
"workers": {
"total": 0.84486014194772,
"count": 63303,
"self": 0.0,
"children": {
"worker_root": {
"total": 2139.378236284968,
"count": 63303,
"is_parallel": true,
"self": 899.7994446109278,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017263009995076573,
"count": 1,
"is_parallel": true,
"self": 0.0004988370010323706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012274639984752866,
"count": 8,
"is_parallel": true,
"self": 0.0012274639984752866
}
}
},
"UnityEnvironment.step": {
"total": 0.05227094199926796,
"count": 1,
"is_parallel": true,
"self": 0.0006032949995642412,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047100099982344545,
"count": 1,
"is_parallel": true,
"self": 0.00047100099982344545
},
"communicator.exchange": {
"total": 0.04943338399971253,
"count": 1,
"is_parallel": true,
"self": 0.04943338399971253
},
"steps_from_proto": {
"total": 0.0017632620001677424,
"count": 1,
"is_parallel": true,
"self": 0.0003505470003801747,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014127149997875676,
"count": 8,
"is_parallel": true,
"self": 0.0014127149997875676
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1239.57879167404,
"count": 63302,
"is_parallel": true,
"self": 35.83501673484261,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.804329547058842,
"count": 63302,
"is_parallel": true,
"self": 24.804329547058842
},
"communicator.exchange": {
"total": 1078.9245536420276,
"count": 63302,
"is_parallel": true,
"self": 1078.9245536420276
},
"steps_from_proto": {
"total": 100.01489175011102,
"count": 63302,
"is_parallel": true,
"self": 19.855097022188602,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.15979472792242,
"count": 506416,
"is_parallel": true,
"self": 80.15979472792242
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 649.2410800730258,
"count": 63303,
"self": 2.6145392189728227,
"children": {
"process_trajectory": {
"total": 126.0222305740499,
"count": 63303,
"self": 125.82484088105048,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19738969299942255,
"count": 2,
"self": 0.19738969299942255
}
}
},
"_update_policy": {
"total": 520.6043102800031,
"count": 446,
"self": 309.19899159498436,
"children": {
"TorchPPOOptimizer.update": {
"total": 211.40531868501876,
"count": 22842,
"self": 211.40531868501876
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.85000042419415e-07,
"count": 1,
"self": 9.85000042419415e-07
},
"TrainerController._save_models": {
"total": 0.08890199299912638,
"count": 1,
"self": 0.001568283998494735,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08733370900063164,
"count": 1,
"self": 0.08733370900063164
}
}
}
}
}
}
}