ppo-Huggy / run_logs /timers.json
miguepez's picture
Huggy
1548ac0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4054715633392334,
"min": 1.4054715633392334,
"max": 1.4295246601104736,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70558.890625,
"min": 68799.3671875,
"max": 78295.390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.96849087893864,
"min": 75.86,
"max": 431.4913793103448,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49427.0,
"min": 48879.0,
"max": 50053.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999947.0,
"min": 49528.0,
"max": 1999947.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999947.0,
"min": 49528.0,
"max": 1999947.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4492716789245605,
"min": 0.11080902069807053,
"max": 2.497499465942383,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1476.9107666015625,
"min": 12.743037223815918,
"max": 1591.512451171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.87586984270643,
"min": 1.981086403131485,
"max": 4.001319098355148,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2337.1495151519775,
"min": 227.82493636012077,
"max": 2520.818516790867,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.87586984270643,
"min": 1.981086403131485,
"max": 4.001319098355148,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2337.1495151519775,
"min": 227.82493636012077,
"max": 2520.818516790867,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017833038654902742,
"min": 0.01352976226141133,
"max": 0.019751225502598876,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05349911596470823,
"min": 0.02705952452282266,
"max": 0.056037127478824306,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053416175105505524,
"min": 0.02052804250270128,
"max": 0.058090047289927796,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16024852531651657,
"min": 0.04105608500540256,
"max": 0.1718601670116186,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4987488337833247e-06,
"min": 3.4987488337833247e-06,
"max": 0.00029535930154689995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0496246501349974e-05,
"min": 1.0496246501349974e-05,
"max": 0.0008442366185878,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116621666666666,
"min": 0.10116621666666666,
"max": 0.19845310000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30349865,
"min": 0.20751380000000003,
"max": 0.5814121999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.819421166666655e-05,
"min": 6.819421166666655e-05,
"max": 0.00492280969,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020458263499999966,
"min": 0.00020458263499999966,
"max": 0.014072468780000002,
"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": "1747239143",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747241817"
},
"total": 2673.612927288,
"count": 1,
"self": 0.4399252899993371,
"children": {
"run_training.setup": {
"total": 0.02440262499999335,
"count": 1,
"self": 0.02440262499999335
},
"TrainerController.start_learning": {
"total": 2673.1485993730003,
"count": 1,
"self": 4.905520879022333,
"children": {
"TrainerController._reset_env": {
"total": 4.058542496999962,
"count": 1,
"self": 4.058542496999962
},
"TrainerController.advance": {
"total": 2664.077885636978,
"count": 232814,
"self": 5.249458223951478,
"children": {
"env_step": {
"total": 2159.97055935701,
"count": 232814,
"self": 1698.6809144750061,
"children": {
"SubprocessEnvManager._take_step": {
"total": 458.2487548840119,
"count": 232814,
"self": 17.21543096201117,
"children": {
"TorchPolicy.evaluate": {
"total": 441.0333239220007,
"count": 222994,
"self": 441.0333239220007
}
}
},
"workers": {
"total": 3.040889997992167,
"count": 232814,
"self": 0.0,
"children": {
"worker_root": {
"total": 2665.4201660820872,
"count": 232814,
"is_parallel": true,
"self": 1286.8643237792312,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00121499900001254,
"count": 1,
"is_parallel": true,
"self": 0.00038425599996116944,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008307430000513705,
"count": 2,
"is_parallel": true,
"self": 0.0008307430000513705
}
}
},
"UnityEnvironment.step": {
"total": 0.03246213399995668,
"count": 1,
"is_parallel": true,
"self": 0.00035083399984614516,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002265110000507775,
"count": 1,
"is_parallel": true,
"self": 0.0002265110000507775
},
"communicator.exchange": {
"total": 0.03106793300003119,
"count": 1,
"is_parallel": true,
"self": 0.03106793300003119
},
"steps_from_proto": {
"total": 0.0008168560000285652,
"count": 1,
"is_parallel": true,
"self": 0.00022906499998498475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005877910000435804,
"count": 2,
"is_parallel": true,
"self": 0.0005877910000435804
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1378.555842302856,
"count": 232813,
"is_parallel": true,
"self": 40.60837644879348,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.2533022959775,
"count": 232813,
"is_parallel": true,
"self": 92.2533022959775
},
"communicator.exchange": {
"total": 1150.9086455971392,
"count": 232813,
"is_parallel": true,
"self": 1150.9086455971392
},
"steps_from_proto": {
"total": 94.78551796094598,
"count": 232813,
"is_parallel": true,
"self": 36.06674072496617,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.718777235979815,
"count": 465626,
"is_parallel": true,
"self": 58.718777235979815
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 498.8578680560164,
"count": 232814,
"self": 7.246319021994964,
"children": {
"process_trajectory": {
"total": 182.87674308302235,
"count": 232814,
"self": 181.5503078660223,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3264352170000393,
"count": 10,
"self": 1.3264352170000393
}
}
},
"_update_policy": {
"total": 308.7348059509991,
"count": 97,
"self": 244.26559173701548,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.4692142139836,
"count": 2910,
"self": 64.4692142139836
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.740001587488223e-07,
"count": 1,
"self": 9.740001587488223e-07
},
"TrainerController._save_models": {
"total": 0.10664938599984453,
"count": 1,
"self": 0.0016467629998260236,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1050026230000185,
"count": 1,
"self": 0.1050026230000185
}
}
}
}
}
}
}