cfalholt's picture
initial commit
2a8e750
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3400995135307312,
"min": 0.3400995135307312,
"max": 1.4034489393234253,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10170.3359375,
"min": 10170.3359375,
"max": 42575.02734375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989953.0,
"min": 29952.0,
"max": 989953.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989953.0,
"min": 29952.0,
"max": 989953.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5563361048698425,
"min": -0.1098141148686409,
"max": 0.6440852880477905,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 151.32342529296875,
"min": -26.35538673400879,
"max": 180.9879608154297,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.022524075582623482,
"min": 0.006889686454087496,
"max": 0.7209805250167847,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.126548767089844,
"min": 1.9360018968582153,
"max": 170.8723907470703,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07047638356397372,
"min": 0.06627396474070964,
"max": 0.07783139323433232,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.986669369895632,
"min": 0.4894711279489927,
"max": 1.0896395052806525,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011983353274228562,
"min": 0.0008868070413719597,
"max": 0.017937104757962896,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.16776694583919988,
"min": 0.006207649289603718,
"max": 0.22940458558635632,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.7976197431985703e-05,
"min": 1.7976197431985703e-05,
"max": 0.0006886848016164572,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00025166676404779985,
"min": 0.00025166676404779985,
"max": 0.008476019489140101,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256801428571428,
"min": 0.10256801428571428,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4359522,
"min": 1.3691136000000002,
"max": 2.6108599000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026654462714285703,
"min": 0.00026654462714285703,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037316247799999984,
"min": 0.0037316247799999984,
"max": 0.12110490401000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01931542158126831,
"min": 0.01931542158126831,
"max": 0.7010008692741394,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.27041590213775635,
"min": 0.27041590213775635,
"max": 4.90700626373291,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 352.48192771084337,
"min": 316.1546391752577,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29256.0,
"min": 15984.0,
"max": 32890.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4720123258453828,
"min": -1.0000000521540642,
"max": 1.642689983546734,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 119.23299839347601,
"min": -32.000001668930054,
"max": 164.26899835467339,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4720123258453828,
"min": -1.0000000521540642,
"max": 1.642689983546734,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 119.23299839347601,
"min": -32.000001668930054,
"max": 164.26899835467339,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07120067706147645,
"min": 0.0682096674956847,
"max": 16.695810707286,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.767254841979593,
"min": 5.767254841979593,
"max": 267.132971316576,
"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": "1675770133",
"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=PyramidsTraining1 --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": "1675772555"
},
"total": 2421.257662558,
"count": 1,
"self": 0.5953151730000172,
"children": {
"run_training.setup": {
"total": 0.12926496200003612,
"count": 1,
"self": 0.12926496200003612
},
"TrainerController.start_learning": {
"total": 2420.533082423,
"count": 1,
"self": 1.496762361950914,
"children": {
"TrainerController._reset_env": {
"total": 9.685728180000012,
"count": 1,
"self": 9.685728180000012
},
"TrainerController.advance": {
"total": 2409.234889120049,
"count": 63802,
"self": 1.7483967760890664,
"children": {
"env_step": {
"total": 1626.1406211719677,
"count": 63802,
"self": 1504.3689731390314,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.85353511799855,
"count": 63802,
"self": 4.944926775981003,
"children": {
"TorchPolicy.evaluate": {
"total": 115.90860834201754,
"count": 62567,
"self": 38.666841744004785,
"children": {
"TorchPolicy.sample_actions": {
"total": 77.24176659801276,
"count": 62567,
"self": 77.24176659801276
}
}
}
}
},
"workers": {
"total": 0.9181129149379217,
"count": 63802,
"self": 0.0,
"children": {
"worker_root": {
"total": 2414.751616176942,
"count": 63802,
"is_parallel": true,
"self": 1034.4889059489765,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0066862179999702676,
"count": 1,
"is_parallel": true,
"self": 0.0038246739999863166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002861543999983951,
"count": 8,
"is_parallel": true,
"self": 0.002861543999983951
}
}
},
"UnityEnvironment.step": {
"total": 0.0683951700000307,
"count": 1,
"is_parallel": true,
"self": 0.0005669070000635656,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044498699998030133,
"count": 1,
"is_parallel": true,
"self": 0.00044498699998030133
},
"communicator.exchange": {
"total": 0.06574333600002547,
"count": 1,
"is_parallel": true,
"self": 0.06574333600002547
},
"steps_from_proto": {
"total": 0.0016399399999613706,
"count": 1,
"is_parallel": true,
"self": 0.0003866629999720317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001253276999989339,
"count": 8,
"is_parallel": true,
"self": 0.001253276999989339
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1380.2627102279657,
"count": 63801,
"is_parallel": true,
"self": 33.97365291900519,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.202625107003996,
"count": 63801,
"is_parallel": true,
"self": 24.202625107003996
},
"communicator.exchange": {
"total": 1221.7159845919773,
"count": 63801,
"is_parallel": true,
"self": 1221.7159845919773
},
"steps_from_proto": {
"total": 100.3704476099793,
"count": 63801,
"is_parallel": true,
"self": 23.80759674097294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.56285086900635,
"count": 510408,
"is_parallel": true,
"self": 76.56285086900635
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 781.3458711719923,
"count": 63802,
"self": 2.951858799997808,
"children": {
"process_trajectory": {
"total": 169.69606737499464,
"count": 63802,
"self": 169.45493380399455,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24113357100009125,
"count": 2,
"self": 0.24113357100009125
}
}
},
"_update_policy": {
"total": 608.6979449969998,
"count": 447,
"self": 237.30174295499882,
"children": {
"TorchPPOOptimizer.update": {
"total": 371.396202042001,
"count": 22782,
"self": 371.396202042001
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2939999578520656e-06,
"count": 1,
"self": 1.2939999578520656e-06
},
"TrainerController._save_models": {
"total": 0.11570146700023543,
"count": 1,
"self": 0.0015210810001917707,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11418038600004365,
"count": 1,
"self": 0.11418038600004365
}
}
}
}
}
}
}