ppo-Huggy / run_logs /timers.json
SolomonHsu's picture
Huggy
20e697f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4106801748275757,
"min": 1.4106801748275757,
"max": 1.4308799505233765,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70515.671875,
"min": 67339.484375,
"max": 79441.734375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 121.5843520782396,
"min": 93.00751879699249,
"max": 386.8062015503876,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49728.0,
"min": 48836.0,
"max": 50228.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999512.0,
"min": 49607.0,
"max": 1999512.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999512.0,
"min": 49607.0,
"max": 1999512.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.288482189178467,
"min": 0.0775984600186348,
"max": 2.4690053462982178,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 935.9891967773438,
"min": 9.932602882385254,
"max": 1268.138671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.398029373152623,
"min": 1.827993536600843,
"max": 4.0227054038567065,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1389.794013619423,
"min": 233.9831726849079,
"max": 2053.448863506317,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.398029373152623,
"min": 1.827993536600843,
"max": 4.0227054038567065,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1389.794013619423,
"min": 233.9831726849079,
"max": 2053.448863506317,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015732642742417133,
"min": 0.013663918378733798,
"max": 0.019943385733737766,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.031465285484834266,
"min": 0.027327836757467597,
"max": 0.058170068310950965,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04916978826125463,
"min": 0.021932661222914852,
"max": 0.06185854921738307,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09833957652250926,
"min": 0.043865322445829705,
"max": 0.1855756476521492,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.663523445524998e-06,
"min": 4.663523445524998e-06,
"max": 0.00029533635155455,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.327046891049997e-06,
"min": 9.327046891049997e-06,
"max": 0.0008440743186419,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10155447499999998,
"min": 0.10155447499999998,
"max": 0.19844545000000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20310894999999995,
"min": 0.20310894999999995,
"max": 0.5813581,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.756830249999998e-05,
"min": 8.756830249999998e-05,
"max": 0.004922427955,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017513660499999997,
"min": 0.00017513660499999997,
"max": 0.01406976919,
"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": "1715009150",
"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=Huggy --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": "1715011631"
},
"total": 2480.275860723,
"count": 1,
"self": 0.6395026259997394,
"children": {
"run_training.setup": {
"total": 0.0533303119999573,
"count": 1,
"self": 0.0533303119999573
},
"TrainerController.start_learning": {
"total": 2479.583027785,
"count": 1,
"self": 4.503039724896553,
"children": {
"TrainerController._reset_env": {
"total": 2.9852987190000704,
"count": 1,
"self": 2.9852987190000704
},
"TrainerController.advance": {
"total": 2471.919568771103,
"count": 231299,
"self": 4.921259939094398,
"children": {
"env_step": {
"total": 1997.1512214880634,
"count": 231299,
"self": 1655.091690854116,
"children": {
"SubprocessEnvManager._take_step": {
"total": 339.04726967300576,
"count": 231299,
"self": 17.82971115301882,
"children": {
"TorchPolicy.evaluate": {
"total": 321.21755851998694,
"count": 223026,
"self": 321.21755851998694
}
}
},
"workers": {
"total": 3.012260960941603,
"count": 231299,
"self": 0.0,
"children": {
"worker_root": {
"total": 2471.90133754196,
"count": 231299,
"is_parallel": true,
"self": 1136.9592483769832,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012253080000164118,
"count": 1,
"is_parallel": true,
"self": 0.0003505439999571536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008747640000592583,
"count": 2,
"is_parallel": true,
"self": 0.0008747640000592583
}
}
},
"UnityEnvironment.step": {
"total": 0.030778923999946528,
"count": 1,
"is_parallel": true,
"self": 0.0003838130000985984,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021302100003595115,
"count": 1,
"is_parallel": true,
"self": 0.00021302100003595115
},
"communicator.exchange": {
"total": 0.02944318199990903,
"count": 1,
"is_parallel": true,
"self": 0.02944318199990903
},
"steps_from_proto": {
"total": 0.0007389079999029491,
"count": 1,
"is_parallel": true,
"self": 0.0001858049998872957,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005531030000156534,
"count": 2,
"is_parallel": true,
"self": 0.0005531030000156534
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1334.9420891649768,
"count": 231298,
"is_parallel": true,
"self": 39.91540953883691,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.15076133694583,
"count": 231298,
"is_parallel": true,
"self": 88.15076133694583
},
"communicator.exchange": {
"total": 1112.1353608040915,
"count": 231298,
"is_parallel": true,
"self": 1112.1353608040915
},
"steps_from_proto": {
"total": 94.74055748510261,
"count": 231298,
"is_parallel": true,
"self": 35.63252781899598,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.10802966610663,
"count": 462596,
"is_parallel": true,
"self": 59.10802966610663
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 469.8470873439453,
"count": 231299,
"self": 6.652824251981542,
"children": {
"process_trajectory": {
"total": 156.89638322296446,
"count": 231299,
"self": 155.42288629896518,
"children": {
"RLTrainer._checkpoint": {
"total": 1.473496923999278,
"count": 10,
"self": 1.473496923999278
}
}
},
"_update_policy": {
"total": 306.2978798689993,
"count": 96,
"self": 245.48088017900488,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.81699968999442,
"count": 2838,
"self": 60.81699968999442
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4679999367217533e-06,
"count": 1,
"self": 1.4679999367217533e-06
},
"TrainerController._save_models": {
"total": 0.1751191020002807,
"count": 1,
"self": 0.002971728000375151,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17214737399990554,
"count": 1,
"self": 0.17214737399990554
}
}
}
}
}
}
}