Shridipta-06's picture
First Push
857749b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.104832649230957,
"min": 1.104832649230957,
"max": 2.869692802429199,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10573.2490234375,
"min": 10573.2490234375,
"max": 29388.5234375,
"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": 12.173169136047363,
"min": 0.31398096680641174,
"max": 12.173169136047363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2373.76806640625,
"min": 60.91230773925781,
"max": 2445.821533203125,
"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": 0.07200737753428524,
"min": 0.06236226297058987,
"max": 0.07575602669898858,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28802951013714095,
"min": 0.24944905188235947,
"max": 0.3621293224494758,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20509597425367318,
"min": 0.10685068035530218,
"max": 0.296159191458833,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8203838970146927,
"min": 0.4274027214212087,
"max": 1.236854559066249,
"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": 24.113636363636363,
"min": 2.9318181818181817,
"max": 24.4,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1061.0,
"min": 129.0,
"max": 1342.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.113636363636363,
"min": 2.9318181818181817,
"max": 24.4,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1061.0,
"min": 129.0,
"max": 1342.0,
"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": "1687539719",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "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": "1687540180"
},
"total": 460.9855627239999,
"count": 1,
"self": 0.38537346899988734,
"children": {
"run_training.setup": {
"total": 0.049268407999988995,
"count": 1,
"self": 0.049268407999988995
},
"TrainerController.start_learning": {
"total": 460.55092084700004,
"count": 1,
"self": 0.5201759339774981,
"children": {
"TrainerController._reset_env": {
"total": 4.232315884000059,
"count": 1,
"self": 4.232315884000059
},
"TrainerController.advance": {
"total": 455.6554876600227,
"count": 18203,
"self": 0.2433568640295789,
"children": {
"env_step": {
"total": 455.4121307959931,
"count": 18203,
"self": 332.93908121797756,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.22562981200656,
"count": 18203,
"self": 1.6424826759995312,
"children": {
"TorchPolicy.evaluate": {
"total": 120.58314713600703,
"count": 18203,
"self": 120.58314713600703
}
}
},
"workers": {
"total": 0.24741976600898852,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.8772029529903,
"count": 18203,
"is_parallel": true,
"self": 216.42823124098175,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00746922899998026,
"count": 1,
"is_parallel": true,
"self": 0.006042102000151317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014271269998289426,
"count": 10,
"is_parallel": true,
"self": 0.0014271269998289426
}
}
},
"UnityEnvironment.step": {
"total": 0.0516090419999955,
"count": 1,
"is_parallel": true,
"self": 0.0004172389999439474,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003637629999957426,
"count": 1,
"is_parallel": true,
"self": 0.0003637629999957426
},
"communicator.exchange": {
"total": 0.04867604300000039,
"count": 1,
"is_parallel": true,
"self": 0.04867604300000039
},
"steps_from_proto": {
"total": 0.0021519970000554167,
"count": 1,
"is_parallel": true,
"self": 0.00038523000011991826,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017667669999354985,
"count": 10,
"is_parallel": true,
"self": 0.0017667669999354985
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.44897171200853,
"count": 18202,
"is_parallel": true,
"self": 10.141184964989634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.169504147006819,
"count": 18202,
"is_parallel": true,
"self": 5.169504147006819
},
"communicator.exchange": {
"total": 193.37268332802216,
"count": 18202,
"is_parallel": true,
"self": 193.37268332802216
},
"steps_from_proto": {
"total": 33.76559927198991,
"count": 18202,
"is_parallel": true,
"self": 6.0987459509105975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.666853321079316,
"count": 182020,
"is_parallel": true,
"self": 27.666853321079316
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017439999987800547,
"count": 1,
"self": 0.00017439999987800547,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.021540743988,
"count": 438697,
"is_parallel": true,
"self": 9.885620267054492,
"children": {
"process_trajectory": {
"total": 246.54319115693409,
"count": 438697,
"is_parallel": true,
"self": 245.36089190793393,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1822992490001525,
"count": 4,
"is_parallel": true,
"self": 1.1822992490001525
}
}
},
"_update_policy": {
"total": 195.59272931999942,
"count": 90,
"is_parallel": true,
"self": 76.98444012900461,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.60828919099481,
"count": 4587,
"is_parallel": true,
"self": 118.60828919099481
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14276696899992203,
"count": 1,
"self": 0.0008601530000760249,
"children": {
"RLTrainer._checkpoint": {
"total": 0.141906815999846,
"count": 1,
"self": 0.141906815999846
}
}
}
}
}
}
}