ppo-Pyramids / run_logs /timers.json
oscarb92's picture
First training of Pyramid
02e1eee
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.43755438923835754,
"min": 0.41926953196525574,
"max": 1.4586215019226074,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13168.63671875,
"min": 12557.9609375,
"max": 44248.7421875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989910.0,
"min": 29952.0,
"max": 989910.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989910.0,
"min": 29952.0,
"max": 989910.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.30568620562553406,
"min": -0.13365863263607025,
"max": 0.3546503484249115,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 80.08978271484375,
"min": -32.07807159423828,
"max": 95.04629516601562,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.022770581766963005,
"min": -0.013262571766972542,
"max": 0.4721548855304718,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.965892314910889,
"min": -3.527844190597534,
"max": 111.90071105957031,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07208188780668554,
"min": 0.06503267119566467,
"max": 0.07371548295294364,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0091464292935974,
"min": 0.5160083806706055,
"max": 1.0772929841700447,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012075789150235232,
"min": 0.0006041677329972524,
"max": 0.01569593464795698,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.16906104810329325,
"min": 0.007854180528964281,
"max": 0.21974308507139775,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.70926171599285e-06,
"min": 7.70926171599285e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010792966402389989,
"min": 0.00010792966402389989,
"max": 0.0036319675893441996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256972142857143,
"min": 0.10256972142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4359761,
"min": 1.3886848,
"max": 2.6106558000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026671517071428553,
"min": 0.00026671517071428553,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037340123899999972,
"min": 0.0037340123899999972,
"max": 0.12108451441999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014438191428780556,
"min": 0.014438191428780556,
"max": 0.49106916785240173,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20213468372821808,
"min": 0.20213468372821808,
"max": 3.4374842643737793,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 522.3928571428571,
"min": 447.95454545454544,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29254.0,
"min": 15984.0,
"max": 32711.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1274210198929435,
"min": -1.0000000521540642,
"max": 1.3370153564673204,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 64.26299813389778,
"min": -29.9880016669631,
"max": 86.90599817037582,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1274210198929435,
"min": -1.0000000521540642,
"max": 1.3370153564673204,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 64.26299813389778,
"min": -29.9880016669631,
"max": 86.90599817037582,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07877844948272564,
"min": 0.06896780228081088,
"max": 9.104583425447345,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.490371620515361,
"min": 4.482907148252707,
"max": 145.67333480715752,
"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": "1676019807",
"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=PyramidsTraining --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": "1676021948"
},
"total": 2141.0840963150004,
"count": 1,
"self": 0.42574825100018643,
"children": {
"run_training.setup": {
"total": 0.12562807700010126,
"count": 1,
"self": 0.12562807700010126
},
"TrainerController.start_learning": {
"total": 2140.532719987,
"count": 1,
"self": 1.1980962920802085,
"children": {
"TrainerController._reset_env": {
"total": 6.116395941000064,
"count": 1,
"self": 6.116395941000064
},
"TrainerController.advance": {
"total": 2133.1347074479195,
"count": 63397,
"self": 1.270721866799704,
"children": {
"env_step": {
"total": 1391.2928753300353,
"count": 63397,
"self": 1284.7134725929939,
"children": {
"SubprocessEnvManager._take_step": {
"total": 105.84512547007057,
"count": 63397,
"self": 4.451442648102102,
"children": {
"TorchPolicy.evaluate": {
"total": 101.39368282196847,
"count": 62575,
"self": 34.60781724907315,
"children": {
"TorchPolicy.sample_actions": {
"total": 66.78586557289532,
"count": 62575,
"self": 66.78586557289532
}
}
}
}
},
"workers": {
"total": 0.7342772669708211,
"count": 63397,
"self": 0.0,
"children": {
"worker_root": {
"total": 2136.2184627919987,
"count": 63397,
"is_parallel": true,
"self": 960.4285999699807,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018605729999308096,
"count": 1,
"is_parallel": true,
"self": 0.0006384299997534981,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012221430001773115,
"count": 8,
"is_parallel": true,
"self": 0.0012221430001773115
}
}
},
"UnityEnvironment.step": {
"total": 0.0856712699999207,
"count": 1,
"is_parallel": true,
"self": 0.0005120119999446615,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004499930000747554,
"count": 1,
"is_parallel": true,
"self": 0.0004499930000747554
},
"communicator.exchange": {
"total": 0.08319297999992159,
"count": 1,
"is_parallel": true,
"self": 0.08319297999992159
},
"steps_from_proto": {
"total": 0.001516284999979689,
"count": 1,
"is_parallel": true,
"self": 0.00036813700012316986,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011481479998565192,
"count": 8,
"is_parallel": true,
"self": 0.0011481479998565192
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1175.789862822018,
"count": 63396,
"is_parallel": true,
"self": 30.171795505873206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.710042467977473,
"count": 63396,
"is_parallel": true,
"self": 21.710042467977473
},
"communicator.exchange": {
"total": 1025.667712126029,
"count": 63396,
"is_parallel": true,
"self": 1025.667712126029
},
"steps_from_proto": {
"total": 98.24031272213824,
"count": 63396,
"is_parallel": true,
"self": 20.79122462611508,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.44908809602316,
"count": 507168,
"is_parallel": true,
"self": 77.44908809602316
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 740.5711102510843,
"count": 63397,
"self": 2.173568298019063,
"children": {
"process_trajectory": {
"total": 158.19763693906225,
"count": 63397,
"self": 157.9563047950628,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24133214399944336,
"count": 2,
"self": 0.24133214399944336
}
}
},
"_update_policy": {
"total": 580.199905014003,
"count": 449,
"self": 224.6796872960099,
"children": {
"TorchPPOOptimizer.update": {
"total": 355.5202177179931,
"count": 22824,
"self": 355.5202177179931
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.90999978967011e-07,
"count": 1,
"self": 9.90999978967011e-07
},
"TrainerController._save_models": {
"total": 0.08351931500010323,
"count": 1,
"self": 0.0013748360001955007,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08214447899990773,
"count": 1,
"self": 0.08214447899990773
}
}
}
}
}
}
}