ppo-Pyramids / run_logs /timers.json
shazzz's picture
First Push
2b4b864 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.599629819393158,
"min": 0.5059385299682617,
"max": 1.3475011587142944,
"count": 10
},
"Pyramids.Policy.Entropy.sum": {
"value": 18056.052734375,
"min": 15234.8212890625,
"max": 40877.796875,
"count": 10
},
"Pyramids.Step.mean": {
"value": 299937.0,
"min": 29876.0,
"max": 299937.0,
"count": 10
},
"Pyramids.Step.sum": {
"value": 299937.0,
"min": 29876.0,
"max": 299937.0,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.06407999992370605,
"min": -0.08377300947904587,
"max": 0.1260421872138977,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -15.443279266357422,
"min": -20.189294815063477,
"max": 29.871997833251953,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03486521169543266,
"min": 0.03486521169543266,
"max": 0.4703199863433838,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.40251636505127,
"min": 8.40251636505127,
"max": 111.46583557128906,
"count": 10
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06665528073668651,
"min": 0.0659730467887623,
"max": 0.0708409442319011,
"count": 10
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9331739303136112,
"min": 0.5435417446077209,
"max": 0.9760828728780373,
"count": 10
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0013290936716116725,
"min": 0.0008538765170754994,
"max": 0.007949723781564465,
"count": 10
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.018607311402563415,
"min": 0.010246518204905993,
"max": 0.06359779025251572,
"count": 10
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.573402332678572e-05,
"min": 1.573402332678572e-05,
"max": 0.00028281175572941665,
"count": 10
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00022027632657500005,
"min": 0.00022027632657500005,
"max": 0.003053585182138333,
"count": 10
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10524464285714287,
"min": 0.10524464285714287,
"max": 0.19427058333333336,
"count": 10
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4734250000000002,
"min": 1.4734250000000002,
"max": 2.217861666666667,
"count": 10
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0005339398214285715,
"min": 0.0005339398214285715,
"max": 0.009427631275,
"count": 10
},
"Pyramids.Policy.Beta.sum": {
"value": 0.007475157500000001,
"min": 0.007475157500000001,
"max": 0.10180438049999999,
"count": 10
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0322943739593029,
"min": 0.0322943739593029,
"max": 0.5086736083030701,
"count": 10
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.45212122797966003,
"min": 0.45212122797966003,
"max": 4.0693888664245605,
"count": 10
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 982.6666666666666,
"min": 906.5714285714286,
"max": 998.2666666666667,
"count": 10
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32428.0,
"min": 17186.0,
"max": 33298.0,
"count": 10
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.8620970204020991,
"min": -0.9324333834151427,
"max": -0.47850004583597183,
"count": 10
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -28.449201673269272,
"min": -29.327601686120033,
"max": -13.202000856399536,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.8620970204020991,
"min": -0.9324333834151427,
"max": -0.47850004583597183,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -28.449201673269272,
"min": -29.327601686120033,
"max": -13.202000856399536,
"count": 10
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.3238650124068513,
"min": 0.3238650124068513,
"max": 9.837597578763962,
"count": 10
},
"Pyramids.Policy.RndReward.sum": {
"value": 10.687545409426093,
"min": 10.11720191128552,
"max": 177.0767564177513,
"count": 10
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1710323913",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710324533"
},
"total": 620.057915522,
"count": 1,
"self": 0.4871585920000143,
"children": {
"run_training.setup": {
"total": 0.049293196999997235,
"count": 1,
"self": 0.049293196999997235
},
"TrainerController.start_learning": {
"total": 619.521463733,
"count": 1,
"self": 0.3832185879816734,
"children": {
"TrainerController._reset_env": {
"total": 2.2970554870000797,
"count": 1,
"self": 2.2970554870000797
},
"TrainerController.advance": {
"total": 616.7305033180185,
"count": 18939,
"self": 0.4071372580162915,
"children": {
"env_step": {
"total": 434.62161004100517,
"count": 18939,
"self": 394.4325869120273,
"children": {
"SubprocessEnvManager._take_step": {
"total": 39.93781932799084,
"count": 18939,
"self": 1.419481331971383,
"children": {
"TorchPolicy.evaluate": {
"total": 38.518337996019454,
"count": 18801,
"self": 38.518337996019454
}
}
},
"workers": {
"total": 0.2512038009870139,
"count": 18939,
"self": 0.0,
"children": {
"worker_root": {
"total": 617.9181912310048,
"count": 18939,
"is_parallel": true,
"self": 259.496082748002,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021149589999822638,
"count": 1,
"is_parallel": true,
"self": 0.0006936429997494997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001421316000232764,
"count": 8,
"is_parallel": true,
"self": 0.001421316000232764
}
}
},
"UnityEnvironment.step": {
"total": 0.11306079400014823,
"count": 1,
"is_parallel": true,
"self": 0.0006469720003678958,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048515499997847655,
"count": 1,
"is_parallel": true,
"self": 0.00048515499997847655
},
"communicator.exchange": {
"total": 0.11005449299977954,
"count": 1,
"is_parallel": true,
"self": 0.11005449299977954
},
"steps_from_proto": {
"total": 0.0018741740000223217,
"count": 1,
"is_parallel": true,
"self": 0.0004333500000939239,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014408239999283978,
"count": 8,
"is_parallel": true,
"self": 0.0014408239999283978
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 358.42210848300283,
"count": 18938,
"is_parallel": true,
"self": 10.17915077599082,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.354304913994156,
"count": 18938,
"is_parallel": true,
"self": 7.354304913994156
},
"communicator.exchange": {
"total": 310.45844801000817,
"count": 18938,
"is_parallel": true,
"self": 310.45844801000817
},
"steps_from_proto": {
"total": 30.430204783009685,
"count": 18938,
"is_parallel": true,
"self": 6.190673180028625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.23953160298106,
"count": 151504,
"is_parallel": true,
"self": 24.23953160298106
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 181.701756018997,
"count": 18939,
"self": 0.6548334029737362,
"children": {
"process_trajectory": {
"total": 37.35671043802154,
"count": 18939,
"self": 37.35671043802154
},
"_update_policy": {
"total": 143.69021217800173,
"count": 127,
"self": 83.25335949400755,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.436852683994175,
"count": 6825,
"self": 60.436852683994175
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2549999155453406e-06,
"count": 1,
"self": 1.2549999155453406e-06
},
"TrainerController._save_models": {
"total": 0.11068508499988639,
"count": 1,
"self": 0.001532421999854705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10915266300003168,
"count": 1,
"self": 0.10915266300003168
}
}
}
}
}
}
}