ppo-Huggy / run_logs /timers.json
rosca's picture
Huggy
73d6293 verified
raw
history blame contribute delete
No virus
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4054150581359863,
"min": 1.4054150581359863,
"max": 1.4282699823379517,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69780.265625,
"min": 69370.5234375,
"max": 75308.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.74654377880184,
"min": 67.17598908594816,
"max": 393.8984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49311.0,
"min": 49164.0,
"max": 50419.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999960.0,
"min": 49909.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999960.0,
"min": 49909.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.565236806869507,
"min": 0.08468654751777649,
"max": 2.565236806869507,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1669.9691162109375,
"min": 10.755191802978516,
"max": 1837.9735107421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.012594026079925,
"min": 1.868124268186374,
"max": 4.03111032279808,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2612.198710978031,
"min": 237.2517820596695,
"max": 2866.3831396102905,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.012594026079925,
"min": 1.868124268186374,
"max": 4.03111032279808,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2612.198710978031,
"min": 237.2517820596695,
"max": 2866.3831396102905,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014385279557771151,
"min": 0.013861625270995622,
"max": 0.01926137922661534,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.043155838673313456,
"min": 0.027723250541991245,
"max": 0.05673657341006522,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056999142799112536,
"min": 0.020206785170982282,
"max": 0.06843116053690512,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17099742839733761,
"min": 0.040413570341964564,
"max": 0.1883892816801866,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.817298727599999e-06,
"min": 3.817298727599999e-06,
"max": 0.000295322176559275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1451896182799997e-05,
"min": 1.1451896182799997e-05,
"max": 0.0008439318186893999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012724,
"min": 0.1012724,
"max": 0.19844072499999993,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038172,
"min": 0.20774055000000002,
"max": 0.5813106000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.349276e-05,
"min": 7.349276e-05,
"max": 0.0049221921775000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022047828000000002,
"min": 0.00022047828000000002,
"max": 0.014067398940000003,
"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": "1715930915",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1715933679"
},
"total": 2763.771628101,
"count": 1,
"self": 0.7924431229994298,
"children": {
"run_training.setup": {
"total": 0.05875835499995219,
"count": 1,
"self": 0.05875835499995219
},
"TrainerController.start_learning": {
"total": 2762.9204266230004,
"count": 1,
"self": 5.319917955038818,
"children": {
"TrainerController._reset_env": {
"total": 2.9319771709999713,
"count": 1,
"self": 2.9319771709999713
},
"TrainerController.advance": {
"total": 2754.493295902962,
"count": 233877,
"self": 5.596189022974613,
"children": {
"env_step": {
"total": 2199.109241297041,
"count": 233877,
"self": 1820.4484669762057,
"children": {
"SubprocessEnvManager._take_step": {
"total": 375.11098887087684,
"count": 233877,
"self": 19.333953335785225,
"children": {
"TorchPolicy.evaluate": {
"total": 355.7770355350916,
"count": 222974,
"self": 355.7770355350916
}
}
},
"workers": {
"total": 3.549785449958506,
"count": 233877,
"self": 0.0,
"children": {
"worker_root": {
"total": 2754.674836731932,
"count": 233877,
"is_parallel": true,
"self": 1292.7618428748256,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000984763000019484,
"count": 1,
"is_parallel": true,
"self": 0.00029672199997321513,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006880410000462689,
"count": 2,
"is_parallel": true,
"self": 0.0006880410000462689
}
}
},
"UnityEnvironment.step": {
"total": 0.03304776599998149,
"count": 1,
"is_parallel": true,
"self": 0.0004319969999642126,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021154199998818513,
"count": 1,
"is_parallel": true,
"self": 0.00021154199998818513
},
"communicator.exchange": {
"total": 0.03155632099998229,
"count": 1,
"is_parallel": true,
"self": 0.03155632099998229
},
"steps_from_proto": {
"total": 0.0008479060000468053,
"count": 1,
"is_parallel": true,
"self": 0.0002185260000260314,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006293800000207739,
"count": 2,
"is_parallel": true,
"self": 0.0006293800000207739
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1461.9129938571064,
"count": 233876,
"is_parallel": true,
"self": 43.460077563875075,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 96.42017929713069,
"count": 233876,
"is_parallel": true,
"self": 96.42017929713069
},
"communicator.exchange": {
"total": 1219.4266181500473,
"count": 233876,
"is_parallel": true,
"self": 1219.4266181500473
},
"steps_from_proto": {
"total": 102.60611884605328,
"count": 233876,
"is_parallel": true,
"self": 38.80835877121041,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.79776007484287,
"count": 467752,
"is_parallel": true,
"self": 63.79776007484287
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 549.7878655829462,
"count": 233877,
"self": 7.708252298964908,
"children": {
"process_trajectory": {
"total": 191.31541698298088,
"count": 233877,
"self": 189.88327651198074,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4321404710001389,
"count": 10,
"self": 1.4321404710001389
}
}
},
"_update_policy": {
"total": 350.7641963010004,
"count": 97,
"self": 285.53975260999175,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.22444369100867,
"count": 2910,
"self": 65.22444369100867
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4809997992415447e-06,
"count": 1,
"self": 1.4809997992415447e-06
},
"TrainerController._save_models": {
"total": 0.1752341129999877,
"count": 1,
"self": 0.0028122540002186724,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17242185899976903,
"count": 1,
"self": 0.17242185899976903
}
}
}
}
}
}
}