ppo-Huggy / run_logs /timers.json
Sebu's picture
Huggy
8350ac7 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4045089483261108,
"min": 1.4045089483261108,
"max": 1.4299174547195435,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71243.71875,
"min": 68895.7421875,
"max": 76413.3828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.83220338983051,
"min": 83.70169491525424,
"max": 427.35897435897436,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49461.0,
"min": 49017.0,
"max": 50272.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999935.0,
"min": 49714.0,
"max": 1999935.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999935.0,
"min": 49714.0,
"max": 1999935.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4095046520233154,
"min": 0.0039663901552557945,
"max": 2.449913501739502,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1421.6077880859375,
"min": 0.46010127663612366,
"max": 1421.6077880859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6903112331689414,
"min": 1.7578776879557247,
"max": 3.956832786363976,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2177.2836275696754,
"min": 203.91381180286407,
"max": 2201.566029191017,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6903112331689414,
"min": 1.7578776879557247,
"max": 3.956832786363976,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2177.2836275696754,
"min": 203.91381180286407,
"max": 2201.566029191017,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015351050854466544,
"min": 0.013063917702432567,
"max": 0.019969445348154598,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04605315256339963,
"min": 0.026127835404865133,
"max": 0.057883924602841336,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05849065184593202,
"min": 0.022232320283850034,
"max": 0.06046720203012228,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17547195553779604,
"min": 0.04446464056770007,
"max": 0.17547195553779604,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.474948841716664e-06,
"min": 3.474948841716664e-06,
"max": 0.000295291126569625,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0424846525149992e-05,
"min": 1.0424846525149992e-05,
"max": 0.000843834018722,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115828333333333,
"min": 0.10115828333333333,
"max": 0.19843037500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30347485,
"min": 0.2074406,
"max": 0.5812780000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.779833833333326e-05,
"min": 6.779833833333326e-05,
"max": 0.0049216757125,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002033950149999998,
"min": 0.0002033950149999998,
"max": 0.0140657722,
"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": "1708594584",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1708596883"
},
"total": 2298.5670695930003,
"count": 1,
"self": 0.44271552400050496,
"children": {
"run_training.setup": {
"total": 0.04885198700003457,
"count": 1,
"self": 0.04885198700003457
},
"TrainerController.start_learning": {
"total": 2298.0755020819997,
"count": 1,
"self": 4.30836141699092,
"children": {
"TrainerController._reset_env": {
"total": 3.55494252699998,
"count": 1,
"self": 3.55494252699998
},
"TrainerController.advance": {
"total": 2290.098625607009,
"count": 232501,
"self": 4.5356350969805135,
"children": {
"env_step": {
"total": 1818.1396491199516,
"count": 232501,
"self": 1502.37220405091,
"children": {
"SubprocessEnvManager._take_step": {
"total": 313.12448858901143,
"count": 232501,
"self": 16.668936195006722,
"children": {
"TorchPolicy.evaluate": {
"total": 296.4555523940047,
"count": 223062,
"self": 296.4555523940047
}
}
},
"workers": {
"total": 2.6429564800301364,
"count": 232501,
"self": 0.0,
"children": {
"worker_root": {
"total": 2291.354484560027,
"count": 232501,
"is_parallel": true,
"self": 1063.4266114609636,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009836759999757305,
"count": 1,
"is_parallel": true,
"self": 0.0002730389999783256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007106369999974049,
"count": 2,
"is_parallel": true,
"self": 0.0007106369999974049
}
}
},
"UnityEnvironment.step": {
"total": 0.030952160999959233,
"count": 1,
"is_parallel": true,
"self": 0.0003296359999467313,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021478700000443496,
"count": 1,
"is_parallel": true,
"self": 0.00021478700000443496
},
"communicator.exchange": {
"total": 0.02970089600000847,
"count": 1,
"is_parallel": true,
"self": 0.02970089600000847
},
"steps_from_proto": {
"total": 0.0007068419999995967,
"count": 1,
"is_parallel": true,
"self": 0.00018467600000349194,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005221659999961048,
"count": 2,
"is_parallel": true,
"self": 0.0005221659999961048
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1227.9278730990632,
"count": 232500,
"is_parallel": true,
"self": 40.54613712097671,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.77468875704028,
"count": 232500,
"is_parallel": true,
"self": 80.77468875704028
},
"communicator.exchange": {
"total": 1016.8273931030377,
"count": 232500,
"is_parallel": true,
"self": 1016.8273931030377
},
"steps_from_proto": {
"total": 89.77965411800852,
"count": 232500,
"is_parallel": true,
"self": 31.49915132100398,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.280502797004544,
"count": 465000,
"is_parallel": true,
"self": 58.280502797004544
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 467.42334139007716,
"count": 232501,
"self": 6.326736582100921,
"children": {
"process_trajectory": {
"total": 145.50149665297624,
"count": 232501,
"self": 144.2611293409767,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2403673119995346,
"count": 10,
"self": 1.2403673119995346
}
}
},
"_update_policy": {
"total": 315.595108155,
"count": 97,
"self": 253.14326018199125,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.45184797300874,
"count": 2910,
"self": 62.45184797300874
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.81999619398266e-07,
"count": 1,
"self": 9.81999619398266e-07
},
"TrainerController._save_models": {
"total": 0.11357154899997113,
"count": 1,
"self": 0.0019196459998056525,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11165190300016548,
"count": 1,
"self": 0.11165190300016548
}
}
}
}
}
}
}