matolszew's picture
Default params
7599ff8
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5193855166435242,
"min": 0.5193855166435242,
"max": 1.4586974382400513,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15490.154296875,
"min": 15490.154296875,
"max": 44251.046875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989967.0,
"min": 29952.0,
"max": 989967.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989967.0,
"min": 29952.0,
"max": 989967.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4763679504394531,
"min": -0.11144330352544785,
"max": 0.4763679504394531,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 131.00119018554688,
"min": -26.74639320373535,
"max": 131.00119018554688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 2.5012567043304443,
"min": -0.2916642427444458,
"max": 2.5012567043304443,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 687.8455810546875,
"min": -78.166015625,
"max": 687.8455810546875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06557857694791717,
"min": 0.06499765446226645,
"max": 0.07289629199464495,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9181000772708405,
"min": 0.5042684113432188,
"max": 1.0934443799196742,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.7241376086825594,
"min": 0.0005805817004585468,
"max": 0.7241376086825594,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 10.137926521555832,
"min": 0.007547562105961109,
"max": 10.137926521555832,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.525018920264287e-06,
"min": 7.525018920264287e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010535026488370002,
"min": 0.00010535026488370002,
"max": 0.0035074886308371998,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250830714285715,
"min": 0.10250830714285715,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4351163,
"min": 1.3886848,
"max": 2.5691628,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002605798835714286,
"min": 0.0002605798835714286,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036481183700000004,
"min": 0.0036481183700000004,
"max": 0.11693936371999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011046865954995155,
"min": 0.011046865954995155,
"max": 0.43453899025917053,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15465612709522247,
"min": 0.15465612709522247,
"max": 3.0417728424072266,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 359.2073170731707,
"min": 359.2073170731707,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29455.0,
"min": 15984.0,
"max": 32502.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5431853431935718,
"min": -1.0000000521540642,
"max": 1.5431853431935718,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 126.54119814187288,
"min": -30.28500172495842,
"max": 126.54119814187288,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5431853431935718,
"min": -1.0000000521540642,
"max": 1.5431853431935718,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 126.54119814187288,
"min": -30.28500172495842,
"max": 126.54119814187288,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04117710396105128,
"min": 0.04117710396105128,
"max": 8.619620678946376,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.376522524806205,
"min": 3.1918978521425743,
"max": 137.913930863142,
"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": "1678218138",
"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=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": "1.22.4",
"end_time_seconds": "1678220319"
},
"total": 2180.9227405419997,
"count": 1,
"self": 0.47714849300018614,
"children": {
"run_training.setup": {
"total": 0.1163085759999376,
"count": 1,
"self": 0.1163085759999376
},
"TrainerController.start_learning": {
"total": 2180.3292834729996,
"count": 1,
"self": 1.3222984029830513,
"children": {
"TrainerController._reset_env": {
"total": 7.066997548000018,
"count": 1,
"self": 7.066997548000018
},
"TrainerController.advance": {
"total": 2171.851632418017,
"count": 63646,
"self": 1.4633962239199718,
"children": {
"env_step": {
"total": 1430.2845995400776,
"count": 63646,
"self": 1315.850404178977,
"children": {
"SubprocessEnvManager._take_step": {
"total": 113.60666984097543,
"count": 63646,
"self": 4.805307725960574,
"children": {
"TorchPolicy.evaluate": {
"total": 108.80136211501485,
"count": 62553,
"self": 37.08340680007086,
"children": {
"TorchPolicy.sample_actions": {
"total": 71.71795531494399,
"count": 62553,
"self": 71.71795531494399
}
}
}
}
},
"workers": {
"total": 0.8275255201251639,
"count": 63646,
"self": 0.0,
"children": {
"worker_root": {
"total": 2175.6049099629117,
"count": 63646,
"is_parallel": true,
"self": 977.1369273549535,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002441822000037064,
"count": 1,
"is_parallel": true,
"self": 0.0008550339998691925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015867880001678714,
"count": 8,
"is_parallel": true,
"self": 0.0015867880001678714
}
}
},
"UnityEnvironment.step": {
"total": 0.049960063999606064,
"count": 1,
"is_parallel": true,
"self": 0.0005384059991229151,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005152369999450457,
"count": 1,
"is_parallel": true,
"self": 0.0005152369999450457
},
"communicator.exchange": {
"total": 0.04717096100011986,
"count": 1,
"is_parallel": true,
"self": 0.04717096100011986
},
"steps_from_proto": {
"total": 0.001735460000418243,
"count": 1,
"is_parallel": true,
"self": 0.00045328100122787873,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012821789991903643,
"count": 8,
"is_parallel": true,
"self": 0.0012821789991903643
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1198.4679826079582,
"count": 63645,
"is_parallel": true,
"self": 31.778738009902554,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.11872305902125,
"count": 63645,
"is_parallel": true,
"self": 25.11872305902125
},
"communicator.exchange": {
"total": 1044.9922980000365,
"count": 63645,
"is_parallel": true,
"self": 1044.9922980000365
},
"steps_from_proto": {
"total": 96.57822353899792,
"count": 63645,
"is_parallel": true,
"self": 23.167680317936174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.41054322106174,
"count": 509160,
"is_parallel": true,
"self": 73.41054322106174
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 740.1036366540193,
"count": 63646,
"self": 2.5091705219792857,
"children": {
"process_trajectory": {
"total": 164.72391107204157,
"count": 63646,
"self": 164.53494488904153,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18896618300004775,
"count": 2,
"self": 0.18896618300004775
}
}
},
"_update_policy": {
"total": 572.8705550599984,
"count": 451,
"self": 224.21469771894363,
"children": {
"TorchPPOOptimizer.update": {
"total": 348.6558573410548,
"count": 22812,
"self": 348.6558573410548
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.559998943586834e-07,
"count": 1,
"self": 9.559998943586834e-07
},
"TrainerController._save_models": {
"total": 0.08835414799978025,
"count": 1,
"self": 0.0014350159990499378,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08691913200073031,
"count": 1,
"self": 0.08691913200073031
}
}
}
}
}
}
}