ppo-Huggy / run_logs /timers.json
gg232's picture
Init Huggy
5b9ee55 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.402296543121338,
"min": 1.402296543121338,
"max": 1.4276114702224731,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72441.234375,
"min": 67871.984375,
"max": 75853.9921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 105.09513742071881,
"min": 101.6728778467909,
"max": 402.758064516129,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49710.0,
"min": 48836.0,
"max": 50172.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999458.0,
"min": 49512.0,
"max": 1999458.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999458.0,
"min": 49512.0,
"max": 1999458.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3676514625549316,
"min": 0.017804516479372978,
"max": 2.3704285621643066,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1119.899169921875,
"min": 2.189955472946167,
"max": 1128.14599609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7075367091070017,
"min": 1.879124470842563,
"max": 3.8794580402897627,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1753.6648634076118,
"min": 231.13230991363525,
"max": 1812.5068318843842,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7075367091070017,
"min": 1.879124470842563,
"max": 3.8794580402897627,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1753.6648634076118,
"min": 231.13230991363525,
"max": 1812.5068318843842,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016627586589311252,
"min": 0.013264396305021364,
"max": 0.01989424228280162,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.033255173178622505,
"min": 0.026528792610042727,
"max": 0.057401319688748724,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053853238746523854,
"min": 0.022530410221467415,
"max": 0.06088936895959907,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10770647749304771,
"min": 0.04506082044293483,
"max": 0.18266810687879723,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.4770735076749985e-06,
"min": 4.4770735076749985e-06,
"max": 0.00029531145156284997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.954147015349997e-06,
"min": 8.954147015349997e-06,
"max": 0.00084402586865805,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101492325,
"min": 0.101492325,
"max": 0.19843714999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20298465,
"min": 0.20298465,
"max": 0.5813419500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.44670175e-05,
"min": 8.44670175e-05,
"max": 0.004922013785,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000168934035,
"min": 0.000168934035,
"max": 0.014068963305000005,
"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": "1718514116",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718516437"
},
"total": 2320.316120211,
"count": 1,
"self": 0.5563170720001835,
"children": {
"run_training.setup": {
"total": 0.08630933199992796,
"count": 1,
"self": 0.08630933199992796
},
"TrainerController.start_learning": {
"total": 2319.673493807,
"count": 1,
"self": 4.161784521007576,
"children": {
"TrainerController._reset_env": {
"total": 3.414217925999992,
"count": 1,
"self": 3.414217925999992
},
"TrainerController.advance": {
"total": 2311.9828074229927,
"count": 230928,
"self": 4.624262411007749,
"children": {
"env_step": {
"total": 1837.28479190601,
"count": 230928,
"self": 1518.2002181687474,
"children": {
"SubprocessEnvManager._take_step": {
"total": 316.3103214031188,
"count": 230928,
"self": 15.810931975111316,
"children": {
"TorchPolicy.evaluate": {
"total": 300.4993894280075,
"count": 223062,
"self": 300.4993894280075
}
}
},
"workers": {
"total": 2.7742523341438527,
"count": 230928,
"self": 0.0,
"children": {
"worker_root": {
"total": 2312.8122201600127,
"count": 230928,
"is_parallel": true,
"self": 1091.1200488880218,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010262740000825943,
"count": 1,
"is_parallel": true,
"self": 0.0002926450001723424,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007336289999102519,
"count": 2,
"is_parallel": true,
"self": 0.0007336289999102519
}
}
},
"UnityEnvironment.step": {
"total": 0.029548646999955963,
"count": 1,
"is_parallel": true,
"self": 0.00037561499993898906,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001984450000236393,
"count": 1,
"is_parallel": true,
"self": 0.0001984450000236393
},
"communicator.exchange": {
"total": 0.028235419999987244,
"count": 1,
"is_parallel": true,
"self": 0.028235419999987244
},
"steps_from_proto": {
"total": 0.0007391670000060913,
"count": 1,
"is_parallel": true,
"self": 0.0001973110000790257,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005418559999270656,
"count": 2,
"is_parallel": true,
"self": 0.0005418559999270656
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1221.692171271991,
"count": 230927,
"is_parallel": true,
"self": 38.024226637028505,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.01265800599674,
"count": 230927,
"is_parallel": true,
"self": 80.01265800599674
},
"communicator.exchange": {
"total": 1016.8146144110001,
"count": 230927,
"is_parallel": true,
"self": 1016.8146144110001
},
"steps_from_proto": {
"total": 86.84067221796545,
"count": 230927,
"is_parallel": true,
"self": 30.949451633916965,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.89122058404848,
"count": 461854,
"is_parallel": true,
"self": 55.89122058404848
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 470.0737531059749,
"count": 230928,
"self": 6.266194404055909,
"children": {
"process_trajectory": {
"total": 141.78902151191744,
"count": 230928,
"self": 140.47449083391678,
"children": {
"RLTrainer._checkpoint": {
"total": 1.314530678000665,
"count": 10,
"self": 1.314530678000665
}
}
},
"_update_policy": {
"total": 322.01853719000155,
"count": 96,
"self": 259.5905958579922,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.42794133200937,
"count": 2880,
"self": 62.42794133200937
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0769999789772555e-06,
"count": 1,
"self": 1.0769999789772555e-06
},
"TrainerController._save_models": {
"total": 0.11468285999990258,
"count": 1,
"self": 0.004058164000070974,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1106246959998316,
"count": 1,
"self": 0.1106246959998316
}
}
}
}
}
}
}