ppo-Huggy / run_logs /timers.json
ApolloFilippou's picture
Huggy
6f7e2f9
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406402587890625,
"min": 1.406402587890625,
"max": 1.427772879600525,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71550.734375,
"min": 68832.796875,
"max": 76525.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 90.57142857142857,
"min": 74.32680722891567,
"max": 418.14166666666665,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49452.0,
"min": 48786.0,
"max": 50177.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999987.0,
"min": 49566.0,
"max": 1999987.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999987.0,
"min": 49566.0,
"max": 1999987.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.416297435760498,
"min": 0.14453734457492828,
"max": 2.4710888862609863,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1319.2984619140625,
"min": 17.19994354248047,
"max": 1569.169189453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.680641334572118,
"min": 1.9302498495378415,
"max": 4.020844091050672,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2009.6301686763763,
"min": 229.69973209500313,
"max": 2518.3864617347717,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.680641334572118,
"min": 1.9302498495378415,
"max": 4.020844091050672,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2009.6301686763763,
"min": 229.69973209500313,
"max": 2518.3864617347717,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017509629372377985,
"min": 0.013696217671652751,
"max": 0.020765969794441237,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05252888811713395,
"min": 0.027392435343305502,
"max": 0.06025315620548402,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05237303061617745,
"min": 0.02034343471750617,
"max": 0.060813473496172166,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15711909184853234,
"min": 0.04068686943501234,
"max": 0.1824404204885165,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3409988863666796e-06,
"min": 3.3409988863666796e-06,
"max": 0.00029535847654717494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0022996659100039e-05,
"min": 1.0022996659100039e-05,
"max": 0.00084400306866565,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111363333333334,
"min": 0.10111363333333334,
"max": 0.198452825,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033409,
"min": 0.20742434999999992,
"max": 0.58133435,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.557030333333357e-05,
"min": 6.557030333333357e-05,
"max": 0.004922795967500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001967109100000007,
"min": 0.0001967109100000007,
"max": 0.014068584065000002,
"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": "1683432959",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"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": "1683435566"
},
"total": 2607.0773941549996,
"count": 1,
"self": 0.8739434369995251,
"children": {
"run_training.setup": {
"total": 0.07006514500017147,
"count": 1,
"self": 0.07006514500017147
},
"TrainerController.start_learning": {
"total": 2606.133385573,
"count": 1,
"self": 5.151480447897484,
"children": {
"TrainerController._reset_env": {
"total": 4.692942979000009,
"count": 1,
"self": 4.692942979000009
},
"TrainerController.advance": {
"total": 2596.0836076951023,
"count": 232506,
"self": 4.9516445500680675,
"children": {
"env_step": {
"total": 2024.2881018869534,
"count": 232506,
"self": 1713.8619466529517,
"children": {
"SubprocessEnvManager._take_step": {
"total": 307.2393793340068,
"count": 232506,
"self": 17.94715728400206,
"children": {
"TorchPolicy.evaluate": {
"total": 289.29222205000474,
"count": 223108,
"self": 289.29222205000474
}
}
},
"workers": {
"total": 3.1867758999949274,
"count": 232506,
"self": 0.0,
"children": {
"worker_root": {
"total": 2597.1452167419993,
"count": 232506,
"is_parallel": true,
"self": 1196.4379819998458,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000868196000055832,
"count": 1,
"is_parallel": true,
"self": 0.0002970820000882668,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005711139999675652,
"count": 2,
"is_parallel": true,
"self": 0.0005711139999675652
}
}
},
"UnityEnvironment.step": {
"total": 0.030502464999926815,
"count": 1,
"is_parallel": true,
"self": 0.0003280519999862008,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00016089699988697248,
"count": 1,
"is_parallel": true,
"self": 0.00016089699988697248
},
"communicator.exchange": {
"total": 0.029234013999939634,
"count": 1,
"is_parallel": true,
"self": 0.029234013999939634
},
"steps_from_proto": {
"total": 0.0007795020001140074,
"count": 1,
"is_parallel": true,
"self": 0.00020918400014124927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005703179999727581,
"count": 2,
"is_parallel": true,
"self": 0.0005703179999727581
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1400.7072347421536,
"count": 232505,
"is_parallel": true,
"self": 41.684396570356284,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.44684130392898,
"count": 232505,
"is_parallel": true,
"self": 81.44684130392898
},
"communicator.exchange": {
"total": 1176.6110849419983,
"count": 232505,
"is_parallel": true,
"self": 1176.6110849419983
},
"steps_from_proto": {
"total": 100.96491192586996,
"count": 232505,
"is_parallel": true,
"self": 35.7951199847887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.16979194108126,
"count": 465010,
"is_parallel": true,
"self": 65.16979194108126
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 566.8438612580806,
"count": 232506,
"self": 7.695771465942698,
"children": {
"process_trajectory": {
"total": 143.70137247113985,
"count": 232506,
"self": 142.2915692781396,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4098031930002435,
"count": 10,
"self": 1.4098031930002435
}
}
},
"_update_policy": {
"total": 415.446717320998,
"count": 97,
"self": 352.7195120199897,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.727205301008325,
"count": 2910,
"self": 62.727205301008325
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1669999366858974e-06,
"count": 1,
"self": 1.1669999366858974e-06
},
"TrainerController._save_models": {
"total": 0.20535328400001163,
"count": 1,
"self": 0.0036148740000498947,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20173840999996173,
"count": 1,
"self": 0.20173840999996173
}
}
}
}
}
}
}