ppo-PyramidsRND / run_logs /timers.json
Rudolph314's picture
Pyramids first push
eda0564 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5022304058074951,
"min": 0.5022304058074951,
"max": 1.4404478073120117,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15091.01953125,
"min": 15091.01953125,
"max": 43697.42578125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989928.0,
"min": 29952.0,
"max": 989928.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989928.0,
"min": 29952.0,
"max": 989928.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5391917824745178,
"min": -0.09371354430913925,
"max": 0.6504647731781006,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 149.8953094482422,
"min": -22.49125099182129,
"max": 186.03292846679688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.23458337783813477,
"min": -0.009244040586054325,
"max": 0.4205356240272522,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 65.21417999267578,
"min": -2.3942065238952637,
"max": 101.34908294677734,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06721086604964166,
"min": 0.06721086604964166,
"max": 0.07436907960628135,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9409521246949832,
"min": 0.49425760968240384,
"max": 1.0606673738751424,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.023176299208509072,
"min": 0.00018794098207277637,
"max": 0.023176299208509072,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.324468188919127,
"min": 0.00206735080280054,
"max": 0.324468188919127,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.59215461217143e-06,
"min": 7.59215461217143e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010629016457040002,
"min": 0.00010629016457040002,
"max": 0.0035082908305698003,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253068571428572,
"min": 0.10253068571428572,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354296000000002,
"min": 1.3886848,
"max": 2.5694301999999998,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002628155028571429,
"min": 0.0002628155028571429,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036794170400000006,
"min": 0.0036794170400000006,
"max": 0.11696607698000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014751069247722626,
"min": 0.014751069247722626,
"max": 0.5013335943222046,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20651496946811676,
"min": 0.20651496946811676,
"max": 3.5093350410461426,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 357.5,
"min": 306.1340206185567,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30030.0,
"min": 15984.0,
"max": 33252.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5472404547035694,
"min": -1.0000000521540642,
"max": 1.6526205979057194,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 129.96819819509983,
"min": -31.998001664876938,
"max": 162.45919826626778,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5472404547035694,
"min": -1.0000000521540642,
"max": 1.6526205979057194,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 129.96819819509983,
"min": -31.998001664876938,
"max": 162.45919826626778,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.054536744301523346,
"min": 0.048960513193742373,
"max": 9.722250569611788,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.581086521327961,
"min": 4.581086521327961,
"max": 155.5560091137886,
"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": "1713405599",
"python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "\\\\?\\C:\\Users\\User\\miniconda3\\envs\\mlagents2\\Scripts\\mlagents-learn ./config/ppo/PyramidsRND.yaml --run-id=Pyramids1 --force",
"mlagents_version": "1.0.0",
"mlagents_envs_version": "1.0.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713407404"
},
"total": 1804.3917729000095,
"count": 1,
"self": 0.007547500004875474,
"children": {
"run_training.setup": {
"total": 0.08253529999637976,
"count": 1,
"self": 0.08253529999637976
},
"TrainerController.start_learning": {
"total": 1804.3016901000083,
"count": 1,
"self": 1.1507498003920773,
"children": {
"TrainerController._reset_env": {
"total": 188.4758612000005,
"count": 1,
"self": 188.4758612000005
},
"TrainerController.advance": {
"total": 1614.5583711996005,
"count": 63782,
"self": 1.1691986992955208,
"children": {
"env_step": {
"total": 868.3339761993266,
"count": 63782,
"self": 657.114918399704,
"children": {
"SubprocessEnvManager._take_step": {
"total": 210.47041499851912,
"count": 63782,
"self": 3.2014173990901327,
"children": {
"TorchPolicy.evaluate": {
"total": 207.26899759942899,
"count": 62570,
"self": 207.26899759942899
}
}
},
"workers": {
"total": 0.748642801103415,
"count": 63782,
"self": 0.0,
"children": {
"worker_root": {
"total": 1618.0446752017597,
"count": 63782,
"is_parallel": true,
"self": 1039.7051337024022,
"children": {
"steps_from_proto": {
"total": 0.0024889000051189214,
"count": 1,
"is_parallel": true,
"self": 0.0008089000184554607,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016799999866634607,
"count": 8,
"is_parallel": true,
"self": 0.0016799999866634607
}
}
},
"UnityEnvironment.step": {
"total": 578.3370525993523,
"count": 63782,
"is_parallel": true,
"self": 14.766969595308183,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.158665203300188,
"count": 63782,
"is_parallel": true,
"self": 12.158665203300188
},
"communicator.exchange": {
"total": 504.8057025993912,
"count": 63782,
"is_parallel": true,
"self": 504.8057025993912
},
"steps_from_proto": {
"total": 46.60571520135272,
"count": 63782,
"is_parallel": true,
"self": 11.001865401573014,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.60384979977971,
"count": 510256,
"is_parallel": true,
"self": 35.60384979977971
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 745.0551963009784,
"count": 63782,
"self": 1.9513776992243947,
"children": {
"process_trajectory": {
"total": 123.23188330170524,
"count": 63782,
"self": 122.95206290170609,
"children": {
"RLTrainer._checkpoint": {
"total": 0.27982039999915287,
"count": 2,
"self": 0.27982039999915287
}
}
},
"_update_policy": {
"total": 619.8719353000488,
"count": 449,
"self": 291.3379866997857,
"children": {
"TorchPPOOptimizer.update": {
"total": 328.5339486002631,
"count": 22800,
"self": 328.5339486002631
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.50000583846122e-06,
"count": 1,
"self": 6.50000583846122e-06
},
"TrainerController._save_models": {
"total": 0.11670140000933316,
"count": 1,
"self": 0.02846990000398364,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08823150000534952,
"count": 1,
"self": 0.08823150000534952
}
}
}
}
}
}
}