testpyramidsrnd / run_logs /timers.json
bothrajat's picture
First Pyramids
94e77ee
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3776736259460449,
"min": 0.3776736259460449,
"max": 1.2476093769073486,
"count": 20
},
"Pyramids.Policy.Entropy.sum": {
"value": 18998.494140625,
"min": 18998.494140625,
"max": 62440.35546875,
"count": 20
},
"Pyramids.Step.mean": {
"value": 999874.0,
"min": 49920.0,
"max": 999874.0,
"count": 20
},
"Pyramids.Step.sum": {
"value": 999874.0,
"min": 49920.0,
"max": 999874.0,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6256685256958008,
"min": -0.06844426691532135,
"max": 0.672815203666687,
"count": 20
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 292.8128662109375,
"min": -27.51459503173828,
"max": 322.9512939453125,
"count": 20
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.018741514533758163,
"min": -0.0005381633527576923,
"max": 0.3810485899448395,
"count": 20
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.771028518676758,
"min": -0.2561657428741455,
"max": 152.03839111328125,
"count": 20
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0697640247633578,
"min": 0.06765343706701613,
"max": 0.07579705501969632,
"count": 20
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.6743365943205872,
"min": 0.9095646602363558,
"max": 1.7159414038070084,
"count": 20
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01741114089500294,
"min": 0.002489177529720798,
"max": 0.01741114089500294,
"count": 20
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.4178673814800705,
"min": 0.04729437306469516,
"max": 0.4178673814800705,
"count": 20
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.3296975567999975e-06,
"min": 7.3296975567999975e-06,
"max": 0.00029215680261440003,
"count": 20
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00017591274136319993,
"min": 0.00017591274136319993,
"max": 0.006032718889093801,
"count": 20
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1024432,
"min": 0.1024432,
"max": 0.19738560000000002,
"count": 20
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.4586368,
"min": 2.3686272,
"max": 4.3109062,
"count": 20
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002540756799999999,
"min": 0.0002540756799999999,
"max": 0.00973882144,
"count": 20
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0060978163199999985,
"min": 0.0060978163199999985,
"max": 0.20111952938000002,
"count": 20
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0150672048330307,
"min": 0.014632516540586948,
"max": 0.37728455662727356,
"count": 20
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.3616129159927368,
"min": 0.35118040442466736,
"max": 4.527414798736572,
"count": 20
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 294.874251497006,
"min": 276.92090395480227,
"max": 999.0,
"count": 20
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 49244.0,
"min": 46491.0,
"max": 53316.0,
"count": 20
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.645226325862065,
"min": -1.0000000521540642,
"max": 1.6778700413171854,
"count": 20
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 274.75279641896486,
"min": -48.00000250339508,
"max": 296.9829973131418,
"count": 20
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.645226325862065,
"min": -1.0000000521540642,
"max": 1.6778700413171854,
"count": 20
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 274.75279641896486,
"min": -48.00000250339508,
"max": 296.9829973131418,
"count": 20
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04574964659164442,
"min": 0.04574964659164442,
"max": 5.083442655702432,
"count": 20
},
"Pyramids.Policy.RndReward.sum": {
"value": 7.6401909808046184,
"min": 7.538699409909896,
"max": 244.00524747371674,
"count": 20
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1657728190",
"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_Training1 --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": "1657731909"
},
"total": 3719.51996703,
"count": 1,
"self": 0.5429586899999777,
"children": {
"run_training.setup": {
"total": 0.08578315099975953,
"count": 1,
"self": 0.08578315099975953
},
"TrainerController.start_learning": {
"total": 3718.891225189,
"count": 1,
"self": 2.896064432078674,
"children": {
"TrainerController._reset_env": {
"total": 5.709341595999831,
"count": 1,
"self": 5.709341595999831
},
"TrainerController.advance": {
"total": 3710.1862332859214,
"count": 64352,
"self": 3.083193245041457,
"children": {
"env_step": {
"total": 2345.712429656001,
"count": 64352,
"self": 2182.784042892131,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.2830565309241,
"count": 64352,
"self": 8.515540034939932,
"children": {
"TorchPolicy.evaluate": {
"total": 152.76751649598418,
"count": 62570,
"self": 34.58320609797693,
"children": {
"TorchPolicy.sample_actions": {
"total": 118.18431039800726,
"count": 62570,
"self": 118.18431039800726
}
}
}
}
},
"workers": {
"total": 1.6453302329459802,
"count": 64352,
"self": 0.0,
"children": {
"worker_root": {
"total": 3711.5316603228575,
"count": 64352,
"is_parallel": true,
"self": 1719.0149781576533,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0033231490001526254,
"count": 1,
"is_parallel": true,
"self": 0.0012802779997400648,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020428710004125605,
"count": 8,
"is_parallel": true,
"self": 0.0020428710004125605
}
}
},
"UnityEnvironment.step": {
"total": 0.08057971700009148,
"count": 1,
"is_parallel": true,
"self": 0.0006640510000579525,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005635749998873507,
"count": 1,
"is_parallel": true,
"self": 0.0005635749998873507
},
"communicator.exchange": {
"total": 0.07720498900016537,
"count": 1,
"is_parallel": true,
"self": 0.07720498900016537
},
"steps_from_proto": {
"total": 0.002147101999980805,
"count": 1,
"is_parallel": true,
"self": 0.000598724999690603,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001548377000290202,
"count": 8,
"is_parallel": true,
"self": 0.001548377000290202
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1992.5166821652042,
"count": 64351,
"is_parallel": true,
"self": 44.97937237126962,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 28.048393197027963,
"count": 64351,
"is_parallel": true,
"self": 28.048393197027963
},
"communicator.exchange": {
"total": 1782.6700106720255,
"count": 64351,
"is_parallel": true,
"self": 1782.6700106720255
},
"steps_from_proto": {
"total": 136.81890592488116,
"count": 64351,
"is_parallel": true,
"self": 37.6737201008591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 99.14518582402206,
"count": 514808,
"is_parallel": true,
"self": 99.14518582402206
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1361.390610384879,
"count": 64352,
"self": 6.0017889249479595,
"children": {
"process_trajectory": {
"total": 251.1647456229298,
"count": 64352,
"self": 249.97967827492994,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1850673479998477,
"count": 10,
"self": 1.1850673479998477
}
}
},
"_update_policy": {
"total": 1104.2240758370012,
"count": 456,
"self": 277.4872305620506,
"children": {
"TorchPPOOptimizer.update": {
"total": 826.7368452749506,
"count": 22851,
"self": 826.7368452749506
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3480002962751314e-06,
"count": 1,
"self": 1.3480002962751314e-06
},
"TrainerController._save_models": {
"total": 0.09958452699993359,
"count": 1,
"self": 0.002081748999444244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09750277800048934,
"count": 1,
"self": 0.09750277800048934
}
}
}
}
}
}
}