testpyramidsrnd / run_logs /timers.json
reachrkr's picture
First Pyramids
742469c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2037947028875351,
"min": 0.1817663013935089,
"max": 1.4590035676956177,
"count": 66
},
"Pyramids.Policy.Entropy.sum": {
"value": 6081.23388671875,
"min": 5493.70458984375,
"max": 44260.33203125,
"count": 66
},
"Pyramids.Step.mean": {
"value": 1979873.0,
"min": 29952.0,
"max": 1979873.0,
"count": 66
},
"Pyramids.Step.sum": {
"value": 1979873.0,
"min": 29952.0,
"max": 1979873.0,
"count": 66
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6487141847610474,
"min": -0.09557998180389404,
"max": 0.6487141847610474,
"count": 66
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 182.93740844726562,
"min": -22.93919563293457,
"max": 182.93740844726562,
"count": 66
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.034488413482904434,
"min": -0.013161281123757362,
"max": 0.28498753905296326,
"count": 66
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.725732803344727,
"min": -3.5535459518432617,
"max": 67.54204559326172,
"count": 66
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07071956194346782,
"min": 0.06450676919529814,
"max": 0.07561143468982275,
"count": 66
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0607934291520174,
"min": 0.5084746882343536,
"max": 1.0809107811456116,
"count": 66
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013694422887912129,
"min": 0.0006279635188514408,
"max": 0.015348352992164327,
"count": 66
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20541634331868194,
"min": 0.00816352574506873,
"max": 0.21487694189030057,
"count": 66
},
"Pyramids.Policy.LearningRate.mean": {
"value": 5.2361582546466685e-06,
"min": 5.2361582546466685e-06,
"max": 0.0002975753150939428,
"count": 66
},
"Pyramids.Policy.LearningRate.sum": {
"value": 7.854237381970003e-05,
"min": 7.854237381970003e-05,
"max": 0.00372679620773465,
"count": 66
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10174535333333333,
"min": 0.10174535333333333,
"max": 0.19919177142857142,
"count": 66
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5261803,
"min": 1.3943424,
"max": 2.65129005,
"count": 66
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0001843607980000001,
"min": 0.0001843607980000001,
"max": 0.009919257965714285,
"count": 66
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0027654119700000015,
"min": 0.0027654119700000015,
"max": 0.12424230846499999,
"count": 66
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.004435162525624037,
"min": 0.004017013590782881,
"max": 0.3488176167011261,
"count": 66
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.06652744114398956,
"min": 0.05815275013446808,
"max": 2.441723346710205,
"count": 66
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 305.1875,
"min": 299.63366336633663,
"max": 999.0,
"count": 66
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29298.0,
"min": 15984.0,
"max": 34525.0,
"count": 66
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6322916502443452,
"min": -1.0000000521540642,
"max": 1.6670715617506127,
"count": 66
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 156.69999842345715,
"min": -30.743001744151115,
"max": 165.73479840904474,
"count": 66
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6322916502443452,
"min": -1.0000000521540642,
"max": 1.6670715617506127,
"count": 66
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 156.69999842345715,
"min": -30.743001744151115,
"max": 165.73479840904474,
"count": 66
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.014429521230037304,
"min": 0.013843038180615016,
"max": 7.171042764559388,
"count": 66
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.3852340380835813,
"min": 1.2757607859675772,
"max": 114.73668423295021,
"count": 66
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 66
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 66
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1659145079",
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1.21.6",
"end_time_seconds": "1659149098"
},
"total": 4018.9136378959997,
"count": 1,
"self": 0.4393358309998803,
"children": {
"run_training.setup": {
"total": 0.04346646800013332,
"count": 1,
"self": 0.04346646800013332
},
"TrainerController.start_learning": {
"total": 4018.4308355969997,
"count": 1,
"self": 2.700215843029582,
"children": {
"TrainerController._reset_env": {
"total": 10.119150063000006,
"count": 1,
"self": 10.119150063000006
},
"TrainerController.advance": {
"total": 4005.5193625459706,
"count": 128251,
"self": 2.7986883328185286,
"children": {
"env_step": {
"total": 2581.956404936209,
"count": 128251,
"self": 2373.9627710532804,
"children": {
"SubprocessEnvManager._take_step": {
"total": 206.5405560760139,
"count": 128251,
"self": 8.989806555949826,
"children": {
"TorchPolicy.evaluate": {
"total": 197.55074952006407,
"count": 125065,
"self": 67.56129452800019,
"children": {
"TorchPolicy.sample_actions": {
"total": 129.98945499206388,
"count": 125065,
"self": 129.98945499206388
}
}
}
}
},
"workers": {
"total": 1.4530778069147345,
"count": 128251,
"self": 0.0,
"children": {
"worker_root": {
"total": 4010.955173267057,
"count": 128251,
"is_parallel": true,
"self": 1835.6164235238075,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050855970000611705,
"count": 1,
"is_parallel": true,
"self": 0.003912888000058956,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011727090000022145,
"count": 8,
"is_parallel": true,
"self": 0.0011727090000022145
}
}
},
"UnityEnvironment.step": {
"total": 0.04683409600011146,
"count": 1,
"is_parallel": true,
"self": 0.0003740180002296256,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005345990000478196,
"count": 1,
"is_parallel": true,
"self": 0.0005345990000478196
},
"communicator.exchange": {
"total": 0.04469885499997872,
"count": 1,
"is_parallel": true,
"self": 0.04469885499997872
},
"steps_from_proto": {
"total": 0.001226623999855292,
"count": 1,
"is_parallel": true,
"self": 0.00031319900017479085,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009134249996805011,
"count": 8,
"is_parallel": true,
"self": 0.0009134249996805011
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2175.3387497432495,
"count": 128250,
"is_parallel": true,
"self": 54.05055168712897,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 44.778581362008936,
"count": 128250,
"is_parallel": true,
"self": 44.778581362008936
},
"communicator.exchange": {
"total": 1895.3572423222486,
"count": 128250,
"is_parallel": true,
"self": 1895.3572423222486
},
"steps_from_proto": {
"total": 181.1523743718633,
"count": 128250,
"is_parallel": true,
"self": 44.384010844710474,
"children": {
"_process_rank_one_or_two_observation": {
"total": 136.76836352715281,
"count": 1026000,
"is_parallel": true,
"self": 136.76836352715281
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1420.7642692769434,
"count": 128251,
"self": 5.086586614012049,
"children": {
"process_trajectory": {
"total": 321.65576124992685,
"count": 128251,
"self": 321.2713950169268,
"children": {
"RLTrainer._checkpoint": {
"total": 0.384366233000037,
"count": 4,
"self": 0.384366233000037
}
}
},
"_update_policy": {
"total": 1094.0219214130045,
"count": 919,
"self": 434.0265647050087,
"children": {
"TorchPPOOptimizer.update": {
"total": 659.9953567079958,
"count": 45588,
"self": 659.9953567079958
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1449992598500103e-06,
"count": 1,
"self": 1.1449992598500103e-06
},
"TrainerController._save_models": {
"total": 0.09210600000005797,
"count": 1,
"self": 0.0019928460005758097,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09011315399948217,
"count": 1,
"self": 0.09011315399948217
}
}
}
}
}
}
}