ppo-Pyramids / run_logs /timers.json
Tingwen's picture
First push
5f2e3e3
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.9969829320907593,
"min": 0.8575412034988403,
"max": 1.4115686416625977,
"count": 17
},
"Pyramids.Policy.Entropy.sum": {
"value": 29861.6328125,
"min": 25657.6328125,
"max": 42821.34765625,
"count": 17
},
"Pyramids.Step.mean": {
"value": 509933.0,
"min": 29964.0,
"max": 509933.0,
"count": 17
},
"Pyramids.Step.sum": {
"value": 509933.0,
"min": 29964.0,
"max": 509933.0,
"count": 17
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.01830919273197651,
"min": -0.14974060654640198,
"max": 0.01830919273197651,
"count": 17
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 4.5223708152771,
"min": -35.63826370239258,
"max": 4.5223708152771,
"count": 17
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.01709148660302162,
"min": 0.01709148660302162,
"max": 0.2620517313480377,
"count": 17
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.221597194671631,
"min": 4.221597194671631,
"max": 62.368309020996094,
"count": 17
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07082497664225848,
"min": 0.06500764627202107,
"max": 0.0723782599125572,
"count": 17
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0623746496338773,
"min": 0.5565264592477129,
"max": 1.0623746496338773,
"count": 17
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0048989031742321405,
"min": 7.02142284882183e-05,
"max": 0.00601692556009361,
"count": 17
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.07348354761348211,
"min": 0.000982999198835056,
"max": 0.07348354761348211,
"count": 17
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.0001514621095126467,
"min": 0.0001514621095126467,
"max": 0.00029484990171670003,
"count": 17
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0022719316426897005,
"min": 0.0022504623498461,
"max": 0.0035096030301324,
"count": 17
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.15048735333333335,
"min": 0.15048735333333335,
"max": 0.19828330000000002,
"count": 17
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.2573103000000003,
"min": 1.5862664000000002,
"max": 2.5698676,
"count": 17
},
"Pyramids.Policy.Beta.mean": {
"value": 0.005053686598,
"min": 0.005053686598,
"max": 0.00982850167,
"count": 17
},
"Pyramids.Policy.Beta.sum": {
"value": 0.07580529897,
"min": 0.07508037460999999,
"max": 0.11700977324,
"count": 17
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.015443197451531887,
"min": 0.015443197451531887,
"max": 0.39791494607925415,
"count": 17
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.23164796829223633,
"min": 0.23164796829223633,
"max": 3.183319568634033,
"count": 17
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 835.4722222222222,
"min": 835.4722222222222,
"max": 999.0,
"count": 17
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30077.0,
"min": 17274.0,
"max": 32230.0,
"count": 17
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.0025000408705737856,
"min": -0.9999032784854213,
"max": -0.0025000408705737856,
"count": 17
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -0.09000147134065628,
"min": -30.997001633048058,
"max": -0.09000147134065628,
"count": 17
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.0025000408705737856,
"min": -0.9999032784854213,
"max": -0.0025000408705737856,
"count": 17
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -0.09000147134065628,
"min": -30.997001633048058,
"max": -0.09000147134065628,
"count": 17
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.1358512864260572,
"min": 0.1358512864260572,
"max": 7.930082940393024,
"count": 17
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.89064631133806,
"min": 4.89064631133806,
"max": 142.74149292707443,
"count": 17
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 17
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 17
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1684572022",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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 --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1684573606"
},
"total": 1583.7547838639998,
"count": 1,
"self": 0.3995960259999265,
"children": {
"run_training.setup": {
"total": 0.04527794199998425,
"count": 1,
"self": 0.04527794199998425
},
"TrainerController.start_learning": {
"total": 1583.309909896,
"count": 1,
"self": 1.1388708590611714,
"children": {
"TrainerController._reset_env": {
"total": 1.4065304709999964,
"count": 1,
"self": 1.4065304709999964
},
"TrainerController.advance": {
"total": 1580.586937227938,
"count": 32505,
"self": 1.1662489229649964,
"children": {
"env_step": {
"total": 1000.4899612489755,
"count": 32505,
"self": 929.3171282380549,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.47137749494686,
"count": 32505,
"self": 3.502615686958052,
"children": {
"TorchPolicy.evaluate": {
"total": 66.96876180798881,
"count": 32259,
"self": 66.96876180798881
}
}
},
"workers": {
"total": 0.7014555159737483,
"count": 32504,
"self": 0.0,
"children": {
"worker_root": {
"total": 1579.9955445599949,
"count": 32504,
"is_parallel": true,
"self": 733.8833108599563,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004127525000058085,
"count": 1,
"is_parallel": true,
"self": 0.0014296180002020265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002697906999856059,
"count": 8,
"is_parallel": true,
"self": 0.002697906999856059
}
}
},
"UnityEnvironment.step": {
"total": 0.15187964100005047,
"count": 1,
"is_parallel": true,
"self": 0.000671200000169847,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005465459998958977,
"count": 1,
"is_parallel": true,
"self": 0.0005465459998958977
},
"communicator.exchange": {
"total": 0.14854791099992326,
"count": 1,
"is_parallel": true,
"self": 0.14854791099992326
},
"steps_from_proto": {
"total": 0.002113984000061464,
"count": 1,
"is_parallel": true,
"self": 0.0004085229998054274,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017054610002560366,
"count": 8,
"is_parallel": true,
"self": 0.0017054610002560366
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 846.1122337000386,
"count": 32503,
"is_parallel": true,
"self": 22.929869145039675,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.172924000007242,
"count": 32503,
"is_parallel": true,
"self": 12.172924000007242
},
"communicator.exchange": {
"total": 742.8078702920088,
"count": 32503,
"is_parallel": true,
"self": 742.8078702920088
},
"steps_from_proto": {
"total": 68.20157026298284,
"count": 32503,
"is_parallel": true,
"self": 14.265620485946101,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.93594977703674,
"count": 260024,
"is_parallel": true,
"self": 53.93594977703674
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 578.9307270559975,
"count": 32504,
"self": 1.9746685670077113,
"children": {
"process_trajectory": {
"total": 73.0058876849946,
"count": 32504,
"self": 72.87605443899452,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12983324600008928,
"count": 1,
"self": 0.12983324600008928
}
}
},
"_update_policy": {
"total": 503.9501708039952,
"count": 225,
"self": 208.54013743900214,
"children": {
"TorchPPOOptimizer.update": {
"total": 295.41003336499307,
"count": 11766,
"self": 295.41003336499307
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6430003597633913e-06,
"count": 1,
"self": 1.6430003597633913e-06
},
"TrainerController._save_models": {
"total": 0.17756969500032938,
"count": 1,
"self": 0.003223708999939845,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17434598600038953,
"count": 1,
"self": 0.17434598600038953
}
}
}
}
}
}
}