testpyramidsrnd / run_logs /timers.json
reachrkr's picture
First Pyramids
10cb65f
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5707029700279236,
"min": 0.5652757883071899,
"max": 1.4192875623703003,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17340.23828125,
"min": 16768.341796875,
"max": 43055.5078125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989984.0,
"min": 29952.0,
"max": 989984.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989984.0,
"min": 29952.0,
"max": 989984.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3308829069137573,
"min": -0.11201882362365723,
"max": 0.4245678186416626,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 87.35308837890625,
"min": -26.996536254882812,
"max": 112.08590698242188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.20673494040966034,
"min": -0.20673494040966034,
"max": 0.3777506947517395,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -54.578025817871094,
"min": -54.578025817871094,
"max": 89.52691650390625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06530816703716048,
"min": 0.06441761891703096,
"max": 0.07412208779848813,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9143143385202468,
"min": 0.5188546145894168,
"max": 1.0496506169147322,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01973478001344206,
"min": 9.869663770396387e-05,
"max": 0.01973478001344206,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.27628692018818884,
"min": 0.0012830562901515303,
"max": 0.27628692018818884,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.657597447500003e-06,
"min": 7.657597447500003e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010720636426500004,
"min": 0.00010720636426500004,
"max": 0.0035078069307311,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025525,
"min": 0.1025525,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.435735,
"min": 1.3886848,
"max": 2.5692689,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002649947500000001,
"min": 0.0002649947500000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037099265000000016,
"min": 0.0037099265000000016,
"max": 0.11694996311000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009012033231556416,
"min": 0.009012033231556416,
"max": 0.5463701486587524,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12616845965385437,
"min": 0.12616845965385437,
"max": 3.8245911598205566,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 486.0169491525424,
"min": 434.28985507246375,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28675.0,
"min": 15984.0,
"max": 33317.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3156633096436658,
"min": -1.0000000521540642,
"max": 1.4542828294847692,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 78.93979857861996,
"min": -31.992801651358604,
"max": 101.79979806393385,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3156633096436658,
"min": -1.0000000521540642,
"max": 1.4542828294847692,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 78.93979857861996,
"min": -31.992801651358604,
"max": 101.79979806393385,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0455802654454601,
"min": 0.04320424944323479,
"max": 12.436921145766973,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.734815926727606,
"min": 2.734815926727606,
"max": 198.99073833227158,
"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": "1658988362",
"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": "1658990412"
},
"total": 2050.333355068,
"count": 1,
"self": 0.48244012299983297,
"children": {
"run_training.setup": {
"total": 0.045549928999889744,
"count": 1,
"self": 0.045549928999889744
},
"TrainerController.start_learning": {
"total": 2049.805365016,
"count": 1,
"self": 1.3576895269975466,
"children": {
"TrainerController._reset_env": {
"total": 10.276445191999983,
"count": 1,
"self": 10.276445191999983
},
"TrainerController.advance": {
"total": 2038.072568757002,
"count": 63535,
"self": 1.463854486995615,
"children": {
"env_step": {
"total": 1303.0495930189945,
"count": 63535,
"self": 1194.6274865239152,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.70092588006867,
"count": 63535,
"self": 4.590606086016464,
"children": {
"TorchPolicy.evaluate": {
"total": 103.1103197940522,
"count": 62576,
"self": 35.43870386903279,
"children": {
"TorchPolicy.sample_actions": {
"total": 67.67161592501941,
"count": 62576,
"self": 67.67161592501941
}
}
}
}
},
"workers": {
"total": 0.7211806150107805,
"count": 63535,
"self": 0.0,
"children": {
"worker_root": {
"total": 2045.8289891430084,
"count": 63535,
"is_parallel": true,
"self": 951.8585412830455,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005277987999988909,
"count": 1,
"is_parallel": true,
"self": 0.003992724000113412,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012852639998754967,
"count": 8,
"is_parallel": true,
"self": 0.0012852639998754967
}
}
},
"UnityEnvironment.step": {
"total": 0.052235718000019915,
"count": 1,
"is_parallel": true,
"self": 0.000574067999991712,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004943810000668236,
"count": 1,
"is_parallel": true,
"self": 0.0004943810000668236
},
"communicator.exchange": {
"total": 0.04933667199998126,
"count": 1,
"is_parallel": true,
"self": 0.04933667199998126
},
"steps_from_proto": {
"total": 0.0018305969999801164,
"count": 1,
"is_parallel": true,
"self": 0.0004934720000164816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013371249999636348,
"count": 8,
"is_parallel": true,
"self": 0.0013371249999636348
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1093.9704478599629,
"count": 63534,
"is_parallel": true,
"self": 28.027807311935703,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.418423961032204,
"count": 63534,
"is_parallel": true,
"self": 23.418423961032204
},
"communicator.exchange": {
"total": 948.0988161160222,
"count": 63534,
"is_parallel": true,
"self": 948.0988161160222
},
"steps_from_proto": {
"total": 94.4254004709727,
"count": 63534,
"is_parallel": true,
"self": 23.034110384859332,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.39129008611337,
"count": 508272,
"is_parallel": true,
"self": 71.39129008611337
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 733.5591212510119,
"count": 63535,
"self": 2.460579467997036,
"children": {
"process_trajectory": {
"total": 165.45096842401574,
"count": 63535,
"self": 165.23889287801592,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2120755459998236,
"count": 2,
"self": 0.2120755459998236
}
}
},
"_update_policy": {
"total": 565.6475733589991,
"count": 450,
"self": 222.9515593279782,
"children": {
"TorchPPOOptimizer.update": {
"total": 342.6960140310209,
"count": 22806,
"self": 342.6960140310209
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1679999261104967e-06,
"count": 1,
"self": 1.1679999261104967e-06
},
"TrainerController._save_models": {
"total": 0.09866037200026767,
"count": 1,
"self": 0.001551199000004999,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09710917300026267,
"count": 1,
"self": 0.09710917300026267
}
}
}
}
}
}
}