Kibalama's picture
First Push
92e906c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9470106363296509,
"min": 0.9119543433189392,
"max": 2.8702824115753174,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9042.0576171875,
"min": 9042.0576171875,
"max": 29394.5625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.69979190826416,
"min": 0.4682201147079468,
"max": 12.69979190826416,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2476.45947265625,
"min": 90.83470153808594,
"max": 2573.836181640625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07085053507220365,
"min": 0.06234483816575341,
"max": 0.07798065079057101,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2834021402888146,
"min": 0.24937935266301364,
"max": 0.3899032539528551,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23856404021966687,
"min": 0.10586616252526165,
"max": 0.3134853281080723,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9542561608786675,
"min": 0.4234646501010466,
"max": 1.4363788006936804,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.545454545454547,
"min": 3.0681818181818183,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1080.0,
"min": 135.0,
"max": 1371.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.545454545454547,
"min": 3.0681818181818183,
"max": 25.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1080.0,
"min": 135.0,
"max": 1371.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1719736965",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1719737407"
},
"total": 442.211954828,
"count": 1,
"self": 0.4356318119999969,
"children": {
"run_training.setup": {
"total": 0.05856176999998297,
"count": 1,
"self": 0.05856176999998297
},
"TrainerController.start_learning": {
"total": 441.717761246,
"count": 1,
"self": 0.5747247550092425,
"children": {
"TrainerController._reset_env": {
"total": 3.155036989999985,
"count": 1,
"self": 3.155036989999985
},
"TrainerController.advance": {
"total": 437.8918470259907,
"count": 18201,
"self": 0.2611138809982094,
"children": {
"env_step": {
"total": 437.6307331449925,
"count": 18201,
"self": 282.91736517697007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.44458333801924,
"count": 18201,
"self": 1.4614856180130573,
"children": {
"TorchPolicy.evaluate": {
"total": 152.98309772000619,
"count": 18201,
"self": 152.98309772000619
}
}
},
"workers": {
"total": 0.2687846300032106,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.5365484759982,
"count": 18201,
"is_parallel": true,
"self": 225.89048706900655,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005821233000006032,
"count": 1,
"is_parallel": true,
"self": 0.00382746400009637,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001993768999909662,
"count": 10,
"is_parallel": true,
"self": 0.001993768999909662
}
}
},
"UnityEnvironment.step": {
"total": 0.06141208300005019,
"count": 1,
"is_parallel": true,
"self": 0.000680419999980586,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003933049999886862,
"count": 1,
"is_parallel": true,
"self": 0.0003933049999886862
},
"communicator.exchange": {
"total": 0.05833262100009051,
"count": 1,
"is_parallel": true,
"self": 0.05833262100009051
},
"steps_from_proto": {
"total": 0.002005736999990404,
"count": 1,
"is_parallel": true,
"self": 0.0003944669999782491,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001611270000012155,
"count": 10,
"is_parallel": true,
"self": 0.001611270000012155
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.64606140699163,
"count": 18200,
"is_parallel": true,
"self": 10.008064350009022,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.249462119993041,
"count": 18200,
"is_parallel": true,
"self": 5.249462119993041
},
"communicator.exchange": {
"total": 166.90028963399175,
"count": 18200,
"is_parallel": true,
"self": 166.90028963399175
},
"steps_from_proto": {
"total": 32.488245302997825,
"count": 18200,
"is_parallel": true,
"self": 6.03690834997019,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.451336953027635,
"count": 182000,
"is_parallel": true,
"self": 26.451336953027635
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012479399993026163,
"count": 1,
"self": 0.00012479399993026163,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 432.59149975302046,
"count": 667359,
"is_parallel": true,
"self": 13.94456710506654,
"children": {
"process_trajectory": {
"total": 240.1898264289532,
"count": 667359,
"is_parallel": true,
"self": 239.549815871953,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6400105570002097,
"count": 4,
"is_parallel": true,
"self": 0.6400105570002097
}
}
},
"_update_policy": {
"total": 178.4571062190007,
"count": 90,
"is_parallel": true,
"self": 56.09195022800429,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.36515599099641,
"count": 4587,
"is_parallel": true,
"self": 122.36515599099641
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09602768100012327,
"count": 1,
"self": 0.001001287000008233,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09502639400011503,
"count": 1,
"self": 0.09502639400011503
}
}
}
}
}
}
}