ppo-Huggy / run_logs /timers.json
YuZhong-Chen's picture
Huggy
c38e800
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4036049842834473,
"min": 1.4036049842834473,
"max": 1.4247028827667236,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69818.1171875,
"min": 68172.4296875,
"max": 75777.1015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.62359550561797,
"min": 78.78309409888357,
"max": 376.89473684210526,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49461.0,
"min": 48815.0,
"max": 50188.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999993.0,
"min": 49949.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999993.0,
"min": 49949.0,
"max": 1999993.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3581459522247314,
"min": 0.055623091757297516,
"max": 2.4621620178222656,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1259.25,
"min": 7.34224796295166,
"max": 1533.927001953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.643257908383559,
"min": 1.7379601751313065,
"max": 3.9489281099686506,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1945.4997230768204,
"min": 229.41074311733246,
"max": 2438.4585759043694,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.643257908383559,
"min": 1.7379601751313065,
"max": 3.9489281099686506,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1945.4997230768204,
"min": 229.41074311733246,
"max": 2438.4585759043694,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014867829320347583,
"min": 0.0129524641612079,
"max": 0.02012144933299472,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04460348796104275,
"min": 0.0259049283224158,
"max": 0.05265765466804926,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05286521886785825,
"min": 0.022900733569016056,
"max": 0.06045841885109742,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15859565660357475,
"min": 0.04580146713803211,
"max": 0.18137525655329226,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.642998785700003e-06,
"min": 3.642998785700003e-06,
"max": 0.0002953278015574,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.092899635710001e-05,
"min": 1.092899635710001e-05,
"max": 0.0008443716185427997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121430000000002,
"min": 0.10121430000000002,
"max": 0.1984426,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30364290000000005,
"min": 0.20761445000000006,
"max": 0.5814571999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.059357000000007e-05,
"min": 7.059357000000007e-05,
"max": 0.004922285740000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002117807100000002,
"min": 0.0002117807100000002,
"max": 0.014074714280000001,
"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": "1696922034",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.21.2",
"end_time_seconds": "1696927142"
},
"total": 5107.443988447,
"count": 1,
"self": 0.6434731910003393,
"children": {
"run_training.setup": {
"total": 0.10540254800002913,
"count": 1,
"self": 0.10540254800002913
},
"TrainerController.start_learning": {
"total": 5106.695112708,
"count": 1,
"self": 9.547759743190909,
"children": {
"TrainerController._reset_env": {
"total": 1.225013190000027,
"count": 1,
"self": 1.225013190000027
},
"TrainerController.advance": {
"total": 5095.802875379808,
"count": 232840,
"self": 9.2633305556692,
"children": {
"env_step": {
"total": 3220.1265071838698,
"count": 232840,
"self": 2682.9704139096348,
"children": {
"SubprocessEnvManager._take_step": {
"total": 531.2229917190591,
"count": 232840,
"self": 36.956489930937096,
"children": {
"TorchPolicy.evaluate": {
"total": 494.266501788122,
"count": 223006,
"self": 494.266501788122
}
}
},
"workers": {
"total": 5.933101555176108,
"count": 232840,
"self": 0.0,
"children": {
"worker_root": {
"total": 5090.133782896045,
"count": 232840,
"is_parallel": true,
"self": 2946.5250748121043,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000905859999875247,
"count": 1,
"is_parallel": true,
"self": 0.00026358099989920447,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006422789999760425,
"count": 2,
"is_parallel": true,
"self": 0.0006422789999760425
}
}
},
"UnityEnvironment.step": {
"total": 0.04021799499992085,
"count": 1,
"is_parallel": true,
"self": 0.0003925779999462975,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002450330000556278,
"count": 1,
"is_parallel": true,
"self": 0.0002450330000556278
},
"communicator.exchange": {
"total": 0.03856747300005736,
"count": 1,
"is_parallel": true,
"self": 0.03856747300005736
},
"steps_from_proto": {
"total": 0.0010129109998615604,
"count": 1,
"is_parallel": true,
"self": 0.0003617719999056135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006511389999559469,
"count": 2,
"is_parallel": true,
"self": 0.0006511389999559469
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2143.6087080839407,
"count": 232839,
"is_parallel": true,
"self": 68.26110823075669,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 101.63722458515099,
"count": 232839,
"is_parallel": true,
"self": 101.63722458515099
},
"communicator.exchange": {
"total": 1817.8455000088888,
"count": 232839,
"is_parallel": true,
"self": 1817.8455000088888
},
"steps_from_proto": {
"total": 155.86487525914436,
"count": 232839,
"is_parallel": true,
"self": 51.82264300104521,
"children": {
"_process_rank_one_or_two_observation": {
"total": 104.04223225809915,
"count": 465678,
"is_parallel": true,
"self": 104.04223225809915
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1866.4130376402688,
"count": 232840,
"self": 14.162748816155045,
"children": {
"process_trajectory": {
"total": 277.17256550511115,
"count": 232840,
"self": 275.6709448941092,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5016206110019539,
"count": 10,
"self": 1.5016206110019539
}
}
},
"_update_policy": {
"total": 1575.0777233190026,
"count": 97,
"self": 477.8606516859945,
"children": {
"TorchPPOOptimizer.update": {
"total": 1097.2170716330081,
"count": 2910,
"self": 1097.2170716330081
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2260006769793108e-06,
"count": 1,
"self": 1.2260006769793108e-06
},
"TrainerController._save_models": {
"total": 0.1194631690004826,
"count": 1,
"self": 0.002874332000828872,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11658883699965372,
"count": 1,
"self": 0.11658883699965372
}
}
}
}
}
}
}