Anastasiaps's picture
First Push
bc430a0
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4101482629776001,
"min": 0.4101482629776001,
"max": 1.4894616603851318,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12435.6953125,
"min": 12308.23046875,
"max": 45184.30859375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989942.0,
"min": 29952.0,
"max": 989942.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989942.0,
"min": 29952.0,
"max": 989942.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5289368629455566,
"min": -0.17163294553756714,
"max": 0.5566861033439636,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 143.87081909179688,
"min": -40.67700958251953,
"max": 154.20205688476562,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.014099959284067154,
"min": -0.014038835652172565,
"max": 0.2932193875312805,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.835188865661621,
"min": -3.9027962684631348,
"max": 70.37265014648438,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0701896207749841,
"min": 0.06325176761127586,
"max": 0.07376859714040399,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9826546908497774,
"min": 0.4935077191226789,
"max": 1.055946725566173,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016186273947456937,
"min": 0.000218747757549441,
"max": 0.01719831132227444,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22660783526439712,
"min": 0.001968729817944969,
"max": 0.24077635851184218,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.610926034485717e-06,
"min": 7.610926034485717e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010655296448280004,
"min": 0.00010655296448280004,
"max": 0.0032540411153197,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253694285714288,
"min": 0.10253694285714288,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355172000000003,
"min": 1.3691136000000002,
"max": 2.4440591000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002634405914285716,
"min": 0.0002634405914285716,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036881682800000023,
"min": 0.0036881682800000023,
"max": 0.10848956197,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013577095232903957,
"min": 0.013577095232903957,
"max": 0.3868127167224884,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19007933139801025,
"min": 0.19007933139801025,
"max": 2.707689046859741,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 357.10843373493975,
"min": 342.6179775280899,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29640.0,
"min": 15984.0,
"max": 31968.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5946867241557823,
"min": -1.0000000521540642,
"max": 1.596933309848492,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 132.35899810492992,
"min": -32.000001668930054,
"max": 141.50399830192327,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5946867241557823,
"min": -1.0000000521540642,
"max": 1.596933309848492,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 132.35899810492992,
"min": -32.000001668930054,
"max": 141.50399830192327,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05070123175532187,
"min": 0.05070123175532187,
"max": 7.34667656943202,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.208202235691715,
"min": 4.208202235691715,
"max": 117.54682511091232,
"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": "1695051529",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1695053800"
},
"total": 2271.289270493,
"count": 1,
"self": 0.4757443910002621,
"children": {
"run_training.setup": {
"total": 0.04142825099984293,
"count": 1,
"self": 0.04142825099984293
},
"TrainerController.start_learning": {
"total": 2270.772097851,
"count": 1,
"self": 1.5449159830823191,
"children": {
"TrainerController._reset_env": {
"total": 4.745156976000089,
"count": 1,
"self": 4.745156976000089
},
"TrainerController.advance": {
"total": 2264.3800068089176,
"count": 63703,
"self": 1.5400382998959685,
"children": {
"env_step": {
"total": 1592.016651509005,
"count": 63703,
"self": 1470.102813675934,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.94308262301001,
"count": 63703,
"self": 5.134912565981722,
"children": {
"TorchPolicy.evaluate": {
"total": 115.80817005702829,
"count": 62572,
"self": 115.80817005702829
}
}
},
"workers": {
"total": 0.9707552100610428,
"count": 63703,
"self": 0.0,
"children": {
"worker_root": {
"total": 2265.4090529289624,
"count": 63703,
"is_parallel": true,
"self": 920.3273153329887,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001925885999980892,
"count": 1,
"is_parallel": true,
"self": 0.0005813339998894662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013445520000914257,
"count": 8,
"is_parallel": true,
"self": 0.0013445520000914257
}
}
},
"UnityEnvironment.step": {
"total": 0.1037671419999242,
"count": 1,
"is_parallel": true,
"self": 0.000632259999974849,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005344480000530893,
"count": 1,
"is_parallel": true,
"self": 0.0005344480000530893
},
"communicator.exchange": {
"total": 0.0949546360000113,
"count": 1,
"is_parallel": true,
"self": 0.0949546360000113
},
"steps_from_proto": {
"total": 0.007645797999884962,
"count": 1,
"is_parallel": true,
"self": 0.002080535000004602,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0055652629998803604,
"count": 8,
"is_parallel": true,
"self": 0.0055652629998803604
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1345.0817375959737,
"count": 63702,
"is_parallel": true,
"self": 34.993249992937535,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.311372826990464,
"count": 63702,
"is_parallel": true,
"self": 24.311372826990464
},
"communicator.exchange": {
"total": 1172.5165942109663,
"count": 63702,
"is_parallel": true,
"self": 1172.5165942109663
},
"steps_from_proto": {
"total": 113.26052056507933,
"count": 63702,
"is_parallel": true,
"self": 22.640961461076586,
"children": {
"_process_rank_one_or_two_observation": {
"total": 90.61955910400275,
"count": 509616,
"is_parallel": true,
"self": 90.61955910400275
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 670.8233170000169,
"count": 63703,
"self": 2.88186196196898,
"children": {
"process_trajectory": {
"total": 116.76695792904661,
"count": 63703,
"self": 116.55896827504625,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2079896540003574,
"count": 2,
"self": 0.2079896540003574
}
}
},
"_update_policy": {
"total": 551.1744971090013,
"count": 442,
"self": 358.056400660025,
"children": {
"TorchPPOOptimizer.update": {
"total": 193.1180964489763,
"count": 22833,
"self": 193.1180964489763
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.044999862642726e-06,
"count": 1,
"self": 1.044999862642726e-06
},
"TrainerController._save_models": {
"total": 0.10201703800021278,
"count": 1,
"self": 0.0014460279999184422,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10057101000029434,
"count": 1,
"self": 0.10057101000029434
}
}
}
}
}
}
}