ppo-Huggy / run_logs /timers.json
dmenini's picture
Huggy
3846fe5
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4020893573760986,
"min": 1.4020811319351196,
"max": 1.4281001091003418,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70506.8671875,
"min": 67472.4765625,
"max": 76353.5625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.47647058823529,
"min": 93.23540489642184,
"max": 383.8,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49203.0,
"min": 49002.0,
"max": 50112.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999993.0,
"min": 49850.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999993.0,
"min": 49850.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3457987308502197,
"min": -0.022381260991096497,
"max": 2.4173061847686768,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1196.3572998046875,
"min": -2.8871827125549316,
"max": 1273.8345947265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6545544703801474,
"min": 1.6903215309446171,
"max": 3.8704116539477327,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1863.8227798938751,
"min": 218.05147749185562,
"max": 2008.8487663269043,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6545544703801474,
"min": 1.6903215309446171,
"max": 3.8704116539477327,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1863.8227798938751,
"min": 218.05147749185562,
"max": 2008.8487663269043,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01654964457395383,
"min": 0.01297345521452371,
"max": 0.020701246323490827,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04964893372186149,
"min": 0.02594691042904742,
"max": 0.05647378629073502,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053481762566500245,
"min": 0.022807090543210506,
"max": 0.06199925504624844,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16044528769950073,
"min": 0.04561418108642101,
"max": 0.17952985788385073,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.406898864399998e-06,
"min": 3.406898864399998e-06,
"max": 0.00029532157655947494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0220696593199993e-05,
"min": 1.0220696593199993e-05,
"max": 0.0008442964685678499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113559999999999,
"min": 0.10113559999999999,
"max": 0.19844052500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034068,
"min": 0.20746450000000002,
"max": 0.5814321500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.666643999999999e-05,
"min": 6.666643999999999e-05,
"max": 0.004922182197500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019999932,
"min": 0.00019999932,
"max": 0.014073464285000004,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677960231",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1677962577"
},
"total": 2345.260804194,
"count": 1,
"self": 0.44314664299963624,
"children": {
"run_training.setup": {
"total": 0.10990208200001916,
"count": 1,
"self": 0.10990208200001916
},
"TrainerController.start_learning": {
"total": 2344.707755469,
"count": 1,
"self": 4.022128671996597,
"children": {
"TrainerController._reset_env": {
"total": 9.76263086900002,
"count": 1,
"self": 9.76263086900002
},
"TrainerController.advance": {
"total": 2330.8067940790033,
"count": 231487,
"self": 4.471711116966617,
"children": {
"env_step": {
"total": 1804.5769196389351,
"count": 231487,
"self": 1507.4154334270625,
"children": {
"SubprocessEnvManager._take_step": {
"total": 294.41297776193375,
"count": 231487,
"self": 15.589302457965573,
"children": {
"TorchPolicy.evaluate": {
"total": 278.8236753039682,
"count": 222970,
"self": 70.83479436591307,
"children": {
"TorchPolicy.sample_actions": {
"total": 207.9888809380551,
"count": 222970,
"self": 207.9888809380551
}
}
}
}
},
"workers": {
"total": 2.748508449939038,
"count": 231487,
"self": 0.0,
"children": {
"worker_root": {
"total": 2336.4582986449304,
"count": 231487,
"is_parallel": true,
"self": 1113.6234359148998,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009849269999904209,
"count": 1,
"is_parallel": true,
"self": 0.0003663089999577096,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006186180000327113,
"count": 2,
"is_parallel": true,
"self": 0.0006186180000327113
}
}
},
"UnityEnvironment.step": {
"total": 0.04568904000001339,
"count": 1,
"is_parallel": true,
"self": 0.00028979600000411665,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002156140000124651,
"count": 1,
"is_parallel": true,
"self": 0.0002156140000124651
},
"communicator.exchange": {
"total": 0.044511202000023786,
"count": 1,
"is_parallel": true,
"self": 0.044511202000023786
},
"steps_from_proto": {
"total": 0.0006724279999730243,
"count": 1,
"is_parallel": true,
"self": 0.00020781900002475595,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004646089999482683,
"count": 2,
"is_parallel": true,
"self": 0.0004646089999482683
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1222.8348627300306,
"count": 231486,
"is_parallel": true,
"self": 38.05812614792512,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.13254300601773,
"count": 231486,
"is_parallel": true,
"self": 78.13254300601773
},
"communicator.exchange": {
"total": 1017.3675250720999,
"count": 231486,
"is_parallel": true,
"self": 1017.3675250720999
},
"steps_from_proto": {
"total": 89.27666850398793,
"count": 231486,
"is_parallel": true,
"self": 35.890881684995236,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.3857868189927,
"count": 462972,
"is_parallel": true,
"self": 53.3857868189927
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 521.7581633231015,
"count": 231487,
"self": 6.596548260198574,
"children": {
"process_trajectory": {
"total": 162.99764653090335,
"count": 231487,
"self": 161.8468804529034,
"children": {
"RLTrainer._checkpoint": {
"total": 1.150766077999947,
"count": 10,
"self": 1.150766077999947
}
}
},
"_update_policy": {
"total": 352.1639685319996,
"count": 97,
"self": 294.46640846299886,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.69756006900076,
"count": 2910,
"self": 57.69756006900076
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.229999366449192e-07,
"count": 1,
"self": 8.229999366449192e-07
},
"TrainerController._save_models": {
"total": 0.11620102599999882,
"count": 1,
"self": 0.0028231840001353703,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11337784199986345,
"count": 1,
"self": 0.11337784199986345
}
}
}
}
}
}
}