ppo-Huggy / run_logs /timers.json
HuggingMachines's picture
Huggy
822d7db verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4062288999557495,
"min": 1.4062288999557495,
"max": 1.4282784461975098,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70750.1875,
"min": 69755.0234375,
"max": 76253.640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 70.47714285714285,
"min": 66.58863328822733,
"max": 406.6422764227642,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49334.0,
"min": 49209.0,
"max": 50017.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49757.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49757.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.468231439590454,
"min": 0.057872120290994644,
"max": 2.506669759750366,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1727.761962890625,
"min": 7.060398578643799,
"max": 1825.5616455078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8442041455847877,
"min": 1.9144382616047,
"max": 4.053732552195108,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2690.9429019093513,
"min": 233.5614679157734,
"max": 2894.950949370861,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8442041455847877,
"min": 1.9144382616047,
"max": 4.053732552195108,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2690.9429019093513,
"min": 233.5614679157734,
"max": 2894.950949370861,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014549006518629741,
"min": 0.014053942495957017,
"max": 0.02089741431021442,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.043647019555889226,
"min": 0.028107884991914033,
"max": 0.05475436599663226,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05995021557642353,
"min": 0.022492383948216836,
"max": 0.06551147972544034,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1798506467292706,
"min": 0.04498476789643367,
"max": 0.1798506467292706,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.974198675300002e-06,
"min": 3.974198675300002e-06,
"max": 0.00029530650156450006,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1922596025900005e-05,
"min": 1.1922596025900005e-05,
"max": 0.0008439924186691999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1013247,
"min": 0.1013247,
"max": 0.19843550000000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039741,
"min": 0.2077817,
"max": 0.5813308000000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.610253000000005e-05,
"min": 7.610253000000005e-05,
"max": 0.00492193145,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022830759000000016,
"min": 0.00022830759000000016,
"max": 0.014068406919999998,
"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": "1763321267",
"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 --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1763323707"
},
"total": 2440.2021589649994,
"count": 1,
"self": 0.4268149179993088,
"children": {
"run_training.setup": {
"total": 0.023956223000368482,
"count": 1,
"self": 0.023956223000368482
},
"TrainerController.start_learning": {
"total": 2439.7513878239997,
"count": 1,
"self": 3.9745267911052906,
"children": {
"TrainerController._reset_env": {
"total": 1.9200867510003263,
"count": 1,
"self": 1.9200867510003263
},
"TrainerController.advance": {
"total": 2433.762654116893,
"count": 233699,
"self": 4.027414356153258,
"children": {
"env_step": {
"total": 1963.3011376949871,
"count": 233699,
"self": 1581.914211424958,
"children": {
"SubprocessEnvManager._take_step": {
"total": 378.9124480508158,
"count": 233699,
"self": 14.01415487592385,
"children": {
"TorchPolicy.evaluate": {
"total": 364.89829317489193,
"count": 222936,
"self": 364.89829317489193
}
}
},
"workers": {
"total": 2.4744782192133243,
"count": 233699,
"self": 0.0,
"children": {
"worker_root": {
"total": 2428.3588655031404,
"count": 233699,
"is_parallel": true,
"self": 1141.1062433863049,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007794240000293939,
"count": 1,
"is_parallel": true,
"self": 0.00019570599988583126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005837180001435627,
"count": 2,
"is_parallel": true,
"self": 0.0005837180001435627
}
}
},
"UnityEnvironment.step": {
"total": 0.02916374000005817,
"count": 1,
"is_parallel": true,
"self": 0.0002584849999038852,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018567100005384418,
"count": 1,
"is_parallel": true,
"self": 0.00018567100005384418
},
"communicator.exchange": {
"total": 0.028069680000044173,
"count": 1,
"is_parallel": true,
"self": 0.028069680000044173
},
"steps_from_proto": {
"total": 0.0006499040000562673,
"count": 1,
"is_parallel": true,
"self": 0.00017555600015839445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004743479998978728,
"count": 2,
"is_parallel": true,
"self": 0.0004743479998978728
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1287.2526221168355,
"count": 233698,
"is_parallel": true,
"self": 36.27514009771585,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.88409302320997,
"count": 233698,
"is_parallel": true,
"self": 78.88409302320997
},
"communicator.exchange": {
"total": 1087.6853837049312,
"count": 233698,
"is_parallel": true,
"self": 1087.6853837049312
},
"steps_from_proto": {
"total": 84.40800529097851,
"count": 233698,
"is_parallel": true,
"self": 29.77925691980363,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.62874837117488,
"count": 467396,
"is_parallel": true,
"self": 54.62874837117488
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 466.43410206575254,
"count": 233699,
"self": 5.910621290997824,
"children": {
"process_trajectory": {
"total": 151.53371293275495,
"count": 233699,
"self": 150.43840662075627,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0953063119986837,
"count": 10,
"self": 1.0953063119986837
}
}
},
"_update_policy": {
"total": 308.98976784199976,
"count": 97,
"self": 246.97651936196553,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.013248480034235,
"count": 2910,
"self": 62.013248480034235
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.130008038482629e-07,
"count": 1,
"self": 9.130008038482629e-07
},
"TrainerController._save_models": {
"total": 0.0941192520003824,
"count": 1,
"self": 0.0016707419999875128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09244851000039489,
"count": 1,
"self": 0.09244851000039489
}
}
}
}
}
}
}