ppo-Huggy / run_logs /timers.json
Belphegor's picture
Huggy
00089dc
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4064778089523315,
"min": 1.4064778089523315,
"max": 1.4275355339050293,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72453.296875,
"min": 69397.7421875,
"max": 75803.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.904,
"min": 76.96567862714508,
"max": 417.3,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49315.0,
"min": 49136.0,
"max": 50076.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49487.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49487.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5192384719848633,
"min": 0.11404948681592941,
"max": 2.5192384719848633,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1574.5240478515625,
"min": 13.57188892364502,
"max": 1574.5240478515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9313481125831604,
"min": 1.8862606362134469,
"max": 3.9529250996311505,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2457.0925703644753,
"min": 224.46501570940018,
"max": 2491.9097706079483,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9313481125831604,
"min": 1.8862606362134469,
"max": 3.9529250996311505,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2457.0925703644753,
"min": 224.46501570940018,
"max": 2491.9097706079483,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018095946176941245,
"min": 0.013655200205458741,
"max": 0.019930623746404308,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05428783853082374,
"min": 0.02843301209844261,
"max": 0.05757073855832763,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05375185662673579,
"min": 0.020920950764169298,
"max": 0.06089739228288333,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16125556988020737,
"min": 0.041841901528338596,
"max": 0.17525870924194653,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7981987339666605e-06,
"min": 3.7981987339666605e-06,
"max": 0.000295361176546275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1394596201899981e-05,
"min": 1.1394596201899981e-05,
"max": 0.0008442678185773999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126603333333335,
"min": 0.10126603333333335,
"max": 0.19845372500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30379810000000007,
"min": 0.2076669,
"max": 0.5814226,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.317506333333324e-05,
"min": 7.317506333333324e-05,
"max": 0.0049228408775,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002195251899999997,
"min": 0.0002195251899999997,
"max": 0.014072987739999997,
"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": "1689084543",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689086945"
},
"total": 2401.599477302,
"count": 1,
"self": 0.7681226090003292,
"children": {
"run_training.setup": {
"total": 0.043649719999962144,
"count": 1,
"self": 0.043649719999962144
},
"TrainerController.start_learning": {
"total": 2400.787704973,
"count": 1,
"self": 4.338504134035247,
"children": {
"TrainerController._reset_env": {
"total": 4.153107961999922,
"count": 1,
"self": 4.153107961999922
},
"TrainerController.advance": {
"total": 2392.104774594965,
"count": 233020,
"self": 4.624011921001966,
"children": {
"env_step": {
"total": 1859.4847568530183,
"count": 233020,
"self": 1563.0227080078341,
"children": {
"SubprocessEnvManager._take_step": {
"total": 293.620722189102,
"count": 233020,
"self": 16.745428461077267,
"children": {
"TorchPolicy.evaluate": {
"total": 276.87529372802476,
"count": 223037,
"self": 276.87529372802476
}
}
},
"workers": {
"total": 2.841326656082174,
"count": 233020,
"self": 0.0,
"children": {
"worker_root": {
"total": 2393.0409406119456,
"count": 233020,
"is_parallel": true,
"self": 1120.1847433178814,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008662420000291604,
"count": 1,
"is_parallel": true,
"self": 0.00023489599993808952,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006313460000910709,
"count": 2,
"is_parallel": true,
"self": 0.0006313460000910709
}
}
},
"UnityEnvironment.step": {
"total": 0.030118292999986807,
"count": 1,
"is_parallel": true,
"self": 0.0003578759999527392,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021220700000412762,
"count": 1,
"is_parallel": true,
"self": 0.00021220700000412762
},
"communicator.exchange": {
"total": 0.02871097499996722,
"count": 1,
"is_parallel": true,
"self": 0.02871097499996722
},
"steps_from_proto": {
"total": 0.0008372350000627193,
"count": 1,
"is_parallel": true,
"self": 0.0002175330000682152,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006197019999945041,
"count": 2,
"is_parallel": true,
"self": 0.0006197019999945041
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1272.8561972940643,
"count": 233019,
"is_parallel": true,
"self": 39.651641161894304,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.3536667521198,
"count": 233019,
"is_parallel": true,
"self": 78.3536667521198
},
"communicator.exchange": {
"total": 1057.7548383090666,
"count": 233019,
"is_parallel": true,
"self": 1057.7548383090666
},
"steps_from_proto": {
"total": 97.09605107098355,
"count": 233019,
"is_parallel": true,
"self": 33.55678335004575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.5392677209378,
"count": 466038,
"is_parallel": true,
"self": 63.5392677209378
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 527.9960058209448,
"count": 233020,
"self": 6.585274006929126,
"children": {
"process_trajectory": {
"total": 138.80061179801635,
"count": 233020,
"self": 137.36578242701603,
"children": {
"RLTrainer._checkpoint": {
"total": 1.434829371000319,
"count": 10,
"self": 1.434829371000319
}
}
},
"_update_policy": {
"total": 382.6101200159993,
"count": 97,
"self": 322.28540209899006,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.32471791700925,
"count": 2910,
"self": 60.32471791700925
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3639996723213699e-06,
"count": 1,
"self": 1.3639996723213699e-06
},
"TrainerController._save_models": {
"total": 0.19131691800021144,
"count": 1,
"self": 0.0026984790001733927,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18861843900003805,
"count": 1,
"self": 0.18861843900003805
}
}
}
}
}
}
}