ppo-Pyramids1 / run_logs /timers.json
colemane's picture
First push
18badc0
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5562538504600525,
"min": 0.5490022897720337,
"max": 1.422965407371521,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16589.71484375,
"min": 16520.828125,
"max": 43167.078125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989924.0,
"min": 29934.0,
"max": 989924.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989924.0,
"min": 29934.0,
"max": 989924.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6909708976745605,
"min": -0.19480161368846893,
"max": 0.6909708976745605,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 184.48922729492188,
"min": -46.75238800048828,
"max": 184.48922729492188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.05492595583200455,
"min": -0.0035984814167022705,
"max": 0.24139218032360077,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 14.665229797363281,
"min": -0.9212112426757812,
"max": 58.175514221191406,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0689696384063508,
"min": 0.06531133918141306,
"max": 0.07273817425359672,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.034544576095262,
"min": 0.4917730203381105,
"max": 1.0419580373369777,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.009071945401309576,
"min": 0.00024218459387452467,
"max": 0.009941023632217409,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.13607918101964364,
"min": 0.0031483997203688207,
"max": 0.13917433085104372,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.447617517493336e-06,
"min": 7.447617517493336e-06,
"max": 0.00029523368730305713,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011171426276240004,
"min": 0.00011171426276240004,
"max": 0.0035074271308576997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248250666666667,
"min": 0.10248250666666667,
"max": 0.19841122857142857,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5372376,
"min": 1.3888786,
"max": 2.5691423,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00013387708266666672,
"min": 0.00013387708266666672,
"max": 0.0049207203057142854,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.002008156240000001,
"min": 0.002008156240000001,
"max": 0.05848020076999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008658763021230698,
"min": 0.008658763021230698,
"max": 0.4141574203968048,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12988144159317017,
"min": 0.12554821372032166,
"max": 2.899101972579956,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 468.2307692307692,
"min": 458.56716417910445,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30435.0,
"min": 16605.0,
"max": 33830.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4086492059322504,
"min": -0.9998129548565033,
"max": 1.4086492059322504,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 91.56219838559628,
"min": -30.994201600551605,
"max": 91.56219838559628,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4086492059322504,
"min": -0.9998129548565033,
"max": 1.4086492059322504,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 91.56219838559628,
"min": -30.994201600551605,
"max": 91.56219838559628,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04159874358402493,
"min": 0.04159874358402493,
"max": 8.204221551909166,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.7039183329616208,
"min": 2.585032766626682,
"max": 139.47176638245583,
"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": "1698444151",
"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": "1698446358"
},
"total": 2206.562752087,
"count": 1,
"self": 1.1010152580001886,
"children": {
"run_training.setup": {
"total": 0.06930566199980603,
"count": 1,
"self": 0.06930566199980603
},
"TrainerController.start_learning": {
"total": 2205.392431167,
"count": 1,
"self": 1.4426283301017975,
"children": {
"TrainerController._reset_env": {
"total": 4.548478286999853,
"count": 1,
"self": 4.548478286999853
},
"TrainerController.advance": {
"total": 2199.2773129728976,
"count": 63464,
"self": 1.4780521898833285,
"children": {
"env_step": {
"total": 1571.322104206985,
"count": 63464,
"self": 1433.0247197449635,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.4046595729783,
"count": 63464,
"self": 4.820053163010016,
"children": {
"TorchPolicy.evaluate": {
"total": 132.58460640996827,
"count": 62565,
"self": 132.58460640996827
}
}
},
"workers": {
"total": 0.8927248890431656,
"count": 63464,
"self": 0.0,
"children": {
"worker_root": {
"total": 2200.322066470032,
"count": 63464,
"is_parallel": true,
"self": 886.6891684710549,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024324239998350095,
"count": 1,
"is_parallel": true,
"self": 0.00067231599950901,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017601080003259995,
"count": 8,
"is_parallel": true,
"self": 0.0017601080003259995
}
}
},
"UnityEnvironment.step": {
"total": 0.0526598589999594,
"count": 1,
"is_parallel": true,
"self": 0.0005546940001295297,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005386150000958878,
"count": 1,
"is_parallel": true,
"self": 0.0005386150000958878
},
"communicator.exchange": {
"total": 0.04991030099972704,
"count": 1,
"is_parallel": true,
"self": 0.04991030099972704
},
"steps_from_proto": {
"total": 0.0016562490000069374,
"count": 1,
"is_parallel": true,
"self": 0.0003746820002561435,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001281566999750794,
"count": 8,
"is_parallel": true,
"self": 0.001281566999750794
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1313.6328979989771,
"count": 63463,
"is_parallel": true,
"self": 35.029477217993644,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.13278092597102,
"count": 63463,
"is_parallel": true,
"self": 24.13278092597102
},
"communicator.exchange": {
"total": 1155.6368430930715,
"count": 63463,
"is_parallel": true,
"self": 1155.6368430930715
},
"steps_from_proto": {
"total": 98.8337967619409,
"count": 63463,
"is_parallel": true,
"self": 20.11559008187669,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.71820668006421,
"count": 507704,
"is_parallel": true,
"self": 78.71820668006421
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 626.4771565760293,
"count": 63464,
"self": 2.7413701320556356,
"children": {
"process_trajectory": {
"total": 120.68064923197426,
"count": 63464,
"self": 120.46899222197453,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21165700999972614,
"count": 2,
"self": 0.21165700999972614
}
}
},
"_update_policy": {
"total": 503.0551372119994,
"count": 454,
"self": 300.1027686560037,
"children": {
"TorchPPOOptimizer.update": {
"total": 202.9523685559957,
"count": 22758,
"self": 202.9523685559957
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2590007827384397e-06,
"count": 1,
"self": 1.2590007827384397e-06
},
"TrainerController._save_models": {
"total": 0.12401031799981865,
"count": 1,
"self": 0.0020402999998623272,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12197001799995633,
"count": 1,
"self": 0.12197001799995633
}
}
}
}
}
}
}