{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5615843534469604,
"min": 0.5615843534469604,
"max": 1.4460688829421997,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16919.4140625,
"min": 16917.642578125,
"max": 43867.9453125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989940.0,
"min": 29952.0,
"max": 989940.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989940.0,
"min": 29952.0,
"max": 989940.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.09780054539442062,
"min": -0.12570631504058838,
"max": 0.10395406931638718,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 24.35233497619629,
"min": -30.295223236083984,
"max": 25.780609130859375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.005890360567718744,
"min": -0.010229737497866154,
"max": 0.29713553190231323,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.4666998386383057,
"min": -2.526745080947876,
"max": 71.31253051757812,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06508188963057708,
"min": 0.06508188963057708,
"max": 0.07324299771762297,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9111464548280792,
"min": 0.46993200672722163,
"max": 1.0254019680467215,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.008716865802300303,
"min": 0.00016897233555048343,
"max": 0.015496035961145285,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.12203612123220425,
"min": 0.002027668026605801,
"max": 0.216944503456034,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.660254589471429e-06,
"min": 7.660254589471429e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010724356425260001,
"min": 0.00010724356425260001,
"max": 0.0031388759537081,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10255338571428572,
"min": 0.10255338571428572,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4357474000000001,
"min": 1.3691136000000002,
"max": 2.3590831999999997,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026508323285714296,
"min": 0.00026508323285714296,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037111652600000013,
"min": 0.0037111652600000013,
"max": 0.10465456081,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012231268920004368,
"min": 0.011495016515254974,
"max": 0.4091203212738037,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1712377667427063,
"min": 0.16093023121356964,
"max": 2.863842248916626,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 773.3243243243244,
"min": 740.8,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28613.0,
"min": 15984.0,
"max": 33336.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.2864841693326047,
"min": -1.0000000521540642,
"max": 0.40683154879431976,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 10.886398434638977,
"min": -32.000001668930054,
"max": 15.45959885418415,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.2864841693326047,
"min": -1.0000000521540642,
"max": 0.40683154879431976,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 10.886398434638977,
"min": -32.000001668930054,
"max": 15.45959885418415,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.09608048498998151,
"min": 0.09292935929261148,
"max": 8.082829795777798,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.6510584296192974,
"min": 3.5313156531192362,
"max": 129.32527673244476,
"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": "1699275319",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699277526"
},
"total": 2206.5452133649997,
"count": 1,
"self": 0.47607568499961417,
"children": {
"run_training.setup": {
"total": 0.043735350000019935,
"count": 1,
"self": 0.043735350000019935
},
"TrainerController.start_learning": {
"total": 2206.02540233,
"count": 1,
"self": 1.261127539975405,
"children": {
"TrainerController._reset_env": {
"total": 7.905802541999947,
"count": 1,
"self": 7.905802541999947
},
"TrainerController.advance": {
"total": 2196.745150456024,
"count": 63216,
"self": 1.4220385670341784,
"children": {
"env_step": {
"total": 1572.043343755996,
"count": 63216,
"self": 1439.8111607450185,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.4302834049886,
"count": 63216,
"self": 4.551224017986613,
"children": {
"TorchPolicy.evaluate": {
"total": 126.87905938700197,
"count": 62552,
"self": 126.87905938700197
}
}
},
"workers": {
"total": 0.801899605988865,
"count": 63216,
"self": 0.0,
"children": {
"worker_root": {
"total": 2201.548952608975,
"count": 63216,
"is_parallel": true,
"self": 872.3169011579516,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004813754999986486,
"count": 1,
"is_parallel": true,
"self": 0.0034969379999552075,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013168170000312784,
"count": 8,
"is_parallel": true,
"self": 0.0013168170000312784
}
}
},
"UnityEnvironment.step": {
"total": 0.07716791100000364,
"count": 1,
"is_parallel": true,
"self": 0.0006729819999691244,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004664900000079797,
"count": 1,
"is_parallel": true,
"self": 0.0004664900000079797
},
"communicator.exchange": {
"total": 0.07438400699999193,
"count": 1,
"is_parallel": true,
"self": 0.07438400699999193
},
"steps_from_proto": {
"total": 0.0016444320000346124,
"count": 1,
"is_parallel": true,
"self": 0.00032451599992100455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013199160001136079,
"count": 8,
"is_parallel": true,
"self": 0.0013199160001136079
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1329.2320514510234,
"count": 63215,
"is_parallel": true,
"self": 34.58961157305748,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.828577428006952,
"count": 63215,
"is_parallel": true,
"self": 24.828577428006952
},
"communicator.exchange": {
"total": 1171.8006321909766,
"count": 63215,
"is_parallel": true,
"self": 1171.8006321909766
},
"steps_from_proto": {
"total": 98.01323025898233,
"count": 63215,
"is_parallel": true,
"self": 19.360161153912486,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.65306910506985,
"count": 505720,
"is_parallel": true,
"self": 78.65306910506985
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 623.2797681329939,
"count": 63216,
"self": 2.3535341860224435,
"children": {
"process_trajectory": {
"total": 118.58503371097305,
"count": 63216,
"self": 118.33342753197286,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25160617900019133,
"count": 2,
"self": 0.25160617900019133
}
}
},
"_update_policy": {
"total": 502.3412002359985,
"count": 434,
"self": 299.7592575990163,
"children": {
"TorchPPOOptimizer.update": {
"total": 202.5819426369822,
"count": 22824,
"self": 202.5819426369822
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7540000953886192e-06,
"count": 1,
"self": 1.7540000953886192e-06
},
"TrainerController._save_models": {
"total": 0.11332003800043822,
"count": 1,
"self": 0.002094477000355255,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11122556100008296,
"count": 1,
"self": 0.11122556100008296
}
}
}
}
}
}
}