ppo-Huggy / run_logs /timers.json
alexeynoskov's picture
Huggy
dde6a4d
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4038218259811401,
"min": 1.4038218259811401,
"max": 1.4299507141113281,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70732.96875,
"min": 68920.421875,
"max": 77110.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.71863799283155,
"min": 80.10696920583469,
"max": 411.344262295082,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49505.0,
"min": 49195.0,
"max": 50184.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49557.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49557.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4155445098876953,
"min": 0.02150166966021061,
"max": 2.4545791149139404,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1345.458251953125,
"min": 2.6017019748687744,
"max": 1472.76611328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.773885572085047,
"min": 2.0290663013280916,
"max": 3.943043953499268,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2102.054263651371,
"min": 245.51702246069908,
"max": 2357.940284192562,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.773885572085047,
"min": 2.0290663013280916,
"max": 3.943043953499268,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2102.054263651371,
"min": 245.51702246069908,
"max": 2357.940284192562,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015070500524982183,
"min": 0.013993831247110695,
"max": 0.020620756506104954,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04521150157494655,
"min": 0.02798766249422139,
"max": 0.0548399043980074,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05165675286617544,
"min": 0.022263563113907973,
"max": 0.05997004962215821,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1549702585985263,
"min": 0.04452712622781595,
"max": 0.17913067489862441,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5428488190833395e-06,
"min": 3.5428488190833395e-06,
"max": 0.00029532600155799993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0628546457250019e-05,
"min": 1.0628546457250019e-05,
"max": 0.0008440114686628502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118091666666668,
"min": 0.10118091666666668,
"max": 0.198442,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354275000000003,
"min": 0.2074912,
"max": 0.5813371500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.892774166666677e-05,
"min": 6.892774166666677e-05,
"max": 0.0049222558,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002067832250000003,
"min": 0.0002067832250000003,
"max": 0.014068723785000002,
"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": "1690749813",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690752314"
},
"total": 2501.185185415,
"count": 1,
"self": 0.7013788429999295,
"children": {
"run_training.setup": {
"total": 0.05401546900000653,
"count": 1,
"self": 0.05401546900000653
},
"TrainerController.start_learning": {
"total": 2500.429791103,
"count": 1,
"self": 4.572753916005695,
"children": {
"TrainerController._reset_env": {
"total": 5.957760652000019,
"count": 1,
"self": 5.957760652000019
},
"TrainerController.advance": {
"total": 2489.716511464994,
"count": 232097,
"self": 5.0326219449775635,
"children": {
"env_step": {
"total": 1921.6160608059458,
"count": 232097,
"self": 1624.421355416898,
"children": {
"SubprocessEnvManager._take_step": {
"total": 294.216933151951,
"count": 232097,
"self": 16.928262744922563,
"children": {
"TorchPolicy.evaluate": {
"total": 277.28867040702846,
"count": 222972,
"self": 277.28867040702846
}
}
},
"workers": {
"total": 2.977772237096815,
"count": 232097,
"self": 0.0,
"children": {
"worker_root": {
"total": 2492.466604327027,
"count": 232097,
"is_parallel": true,
"self": 1165.563157475923,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011660710000001018,
"count": 1,
"is_parallel": true,
"self": 0.0003427460000295923,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008233249999705095,
"count": 2,
"is_parallel": true,
"self": 0.0008233249999705095
}
}
},
"UnityEnvironment.step": {
"total": 0.030170877000017526,
"count": 1,
"is_parallel": true,
"self": 0.00034568200001672267,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021908400000825168,
"count": 1,
"is_parallel": true,
"self": 0.00021908400000825168
},
"communicator.exchange": {
"total": 0.028840121000001773,
"count": 1,
"is_parallel": true,
"self": 0.028840121000001773
},
"steps_from_proto": {
"total": 0.0007659899999907793,
"count": 1,
"is_parallel": true,
"self": 0.00021445400003017312,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005515359999606062,
"count": 2,
"is_parallel": true,
"self": 0.0005515359999606062
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1326.9034468511043,
"count": 232096,
"is_parallel": true,
"self": 41.1352122350761,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.09092235694482,
"count": 232096,
"is_parallel": true,
"self": 82.09092235694482
},
"communicator.exchange": {
"total": 1104.9578968890498,
"count": 232096,
"is_parallel": true,
"self": 1104.9578968890498
},
"steps_from_proto": {
"total": 98.7194153700334,
"count": 232096,
"is_parallel": true,
"self": 35.67356289716628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.045852472867125,
"count": 464192,
"is_parallel": true,
"self": 63.045852472867125
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 563.0678287140702,
"count": 232097,
"self": 6.807644676138352,
"children": {
"process_trajectory": {
"total": 138.842794934931,
"count": 232097,
"self": 137.48808640293092,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3547085320000747,
"count": 10,
"self": 1.3547085320000747
}
}
},
"_update_policy": {
"total": 417.41738910300086,
"count": 97,
"self": 356.7240729349995,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.69331616800133,
"count": 2910,
"self": 60.69331616800133
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3250000847619958e-06,
"count": 1,
"self": 1.3250000847619958e-06
},
"TrainerController._save_models": {
"total": 0.18276374500010206,
"count": 1,
"self": 0.002720859999953973,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1800428850001481,
"count": 1,
"self": 0.1800428850001481
}
}
}
}
}
}
}