ppo-Pyramids / run_logs /timers.json
yovchev's picture
First Push
1768ee6
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7433551549911499,
"min": 0.7143504023551941,
"max": 1.4340167045593262,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 22146.037109375,
"min": 21327.646484375,
"max": 43502.33203125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989917.0,
"min": 29952.0,
"max": 989917.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989917.0,
"min": 29952.0,
"max": 989917.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.15413157641887665,
"min": -0.11687472462654114,
"max": 0.24819843471050262,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 39.14942169189453,
"min": -28.28368377685547,
"max": 62.79420471191406,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.656913697719574,
"min": -0.7782626748085022,
"max": 0.36598485708236694,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -166.8560791015625,
"min": -196.90045166015625,
"max": 88.5683364868164,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0650207949591134,
"min": 0.0648015342945548,
"max": 0.07660426488433879,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.975311924386701,
"min": 0.5362298541903715,
"max": 1.0404246523223049,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.1590801267348438,
"min": 9.33707038638025e-05,
"max": 0.1590801267348438,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 2.386201901022657,
"min": 0.0012138191502294325,
"max": 2.386201901022657,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.485817504760002e-06,
"min": 7.485817504760002e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011228726257140004,
"min": 0.00011228726257140004,
"max": 0.0033823277725574994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249524,
"min": 0.10249524,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5374286,
"min": 1.3886848,
"max": 2.5274425,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025927447600000014,
"min": 0.00025927447600000014,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003889117140000002,
"min": 0.003889117140000002,
"max": 0.11277150575,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014001459814608097,
"min": 0.014001459814608097,
"max": 0.5664225816726685,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.21002189815044403,
"min": 0.20040105283260345,
"max": 3.9649581909179688,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 655.1363636363636,
"min": 570.9298245614035,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28826.0,
"min": 15984.0,
"max": 33260.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.8447272396561775,
"min": -1.0000000521540642,
"max": 1.1833964579722338,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 37.16799854487181,
"min": -31.997601687908173,
"max": 67.45359810441732,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.8447272396561775,
"min": -1.0000000521540642,
"max": 1.1833964579722338,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 37.16799854487181,
"min": -31.997601687908173,
"max": 67.45359810441732,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.09602976514592725,
"min": 0.08488075220916551,
"max": 12.800713658332825,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.225309666420799,
"min": 3.8221125779673457,
"max": 204.8114185333252,
"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": "1678360533",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.20.0",
"end_time_seconds": "1678362652"
},
"total": 2119.1495622089997,
"count": 1,
"self": 1.0722428179997223,
"children": {
"run_training.setup": {
"total": 0.017518420999977025,
"count": 1,
"self": 0.017518420999977025
},
"TrainerController.start_learning": {
"total": 2118.05980097,
"count": 1,
"self": 1.2705373729972962,
"children": {
"TrainerController._reset_env": {
"total": 5.539576416000045,
"count": 1,
"self": 5.539576416000045
},
"TrainerController.advance": {
"total": 2111.1225784430026,
"count": 63234,
"self": 1.3630752970721005,
"children": {
"env_step": {
"total": 1331.5993631189565,
"count": 63234,
"self": 1220.9181419139795,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.90885150699296,
"count": 63234,
"self": 4.740942673999825,
"children": {
"TorchPolicy.evaluate": {
"total": 105.16790883299313,
"count": 62560,
"self": 36.06285629292893,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.10505254006421,
"count": 62560,
"self": 69.10505254006421
}
}
}
}
},
"workers": {
"total": 0.7723696979840042,
"count": 63234,
"self": 0.0,
"children": {
"worker_root": {
"total": 2113.0748885200264,
"count": 63234,
"is_parallel": true,
"self": 1001.6996779680187,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025759239999842976,
"count": 1,
"is_parallel": true,
"self": 0.0008076249998794083,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017682990001048893,
"count": 8,
"is_parallel": true,
"self": 0.0017682990001048893
}
}
},
"UnityEnvironment.step": {
"total": 0.07777447799981019,
"count": 1,
"is_parallel": true,
"self": 0.0008811969996713742,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046634099999209866,
"count": 1,
"is_parallel": true,
"self": 0.00046634099999209866
},
"communicator.exchange": {
"total": 0.07462411400001656,
"count": 1,
"is_parallel": true,
"self": 0.07462411400001656
},
"steps_from_proto": {
"total": 0.0018028260001301533,
"count": 1,
"is_parallel": true,
"self": 0.00046441200015578943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013384139999743638,
"count": 8,
"is_parallel": true,
"self": 0.0013384139999743638
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1111.3752105520077,
"count": 63233,
"is_parallel": true,
"self": 31.27916065905879,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.59265722198961,
"count": 63233,
"is_parallel": true,
"self": 21.59265722198961
},
"communicator.exchange": {
"total": 963.621374900019,
"count": 63233,
"is_parallel": true,
"self": 963.621374900019
},
"steps_from_proto": {
"total": 94.88201777094037,
"count": 63233,
"is_parallel": true,
"self": 22.57894538114988,
"children": {
"_process_rank_one_or_two_observation": {
"total": 72.30307238979049,
"count": 505864,
"is_parallel": true,
"self": 72.30307238979049
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 778.160140026974,
"count": 63234,
"self": 2.3761557059010556,
"children": {
"process_trajectory": {
"total": 156.94695251107441,
"count": 63234,
"self": 156.71657393207443,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23037857899998926,
"count": 2,
"self": 0.23037857899998926
}
}
},
"_update_policy": {
"total": 618.8370318099985,
"count": 442,
"self": 244.83980331796056,
"children": {
"TorchPPOOptimizer.update": {
"total": 373.99722849203795,
"count": 22845,
"self": 373.99722849203795
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1619999895629007e-06,
"count": 1,
"self": 1.1619999895629007e-06
},
"TrainerController._save_models": {
"total": 0.12710757600007128,
"count": 1,
"self": 0.0017989389998547267,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12530863700021655,
"count": 1,
"self": 0.12530863700021655
}
}
}
}
}
}
}