yovchev's picture
First Push
f6413f3
raw
history blame
18.9 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8874013423919678,
"min": 0.8874013423919678,
"max": 2.857954740524292,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8472.908203125,
"min": 8472.908203125,
"max": 29268.314453125,
"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": 12.681095123291016,
"min": 0.3832017481327057,
"max": 12.681095123291016,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2472.8134765625,
"min": 74.34114074707031,
"max": 2553.427001953125,
"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": 0.0679903722627262,
"min": 0.06300367201009638,
"max": 0.07804944020448887,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2719614890509048,
"min": 0.2520146880403855,
"max": 0.39024720102244437,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21370856230165444,
"min": 0.1342301500787703,
"max": 0.29333749230878026,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8548342492066178,
"min": 0.5369206003150812,
"max": 1.314235303039644,
"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": 25.068181818181817,
"min": 3.590909090909091,
"max": 25.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1103.0,
"min": 158.0,
"max": 1368.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.068181818181817,
"min": 3.590909090909091,
"max": 25.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1103.0,
"min": 158.0,
"max": 1368.0,
"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": "1678359466",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.20.0",
"end_time_seconds": "1678359922"
},
"total": 455.908596529,
"count": 1,
"self": 0.4370323530000064,
"children": {
"run_training.setup": {
"total": 0.027007459000003564,
"count": 1,
"self": 0.027007459000003564
},
"TrainerController.start_learning": {
"total": 455.444556717,
"count": 1,
"self": 0.5424616969976341,
"children": {
"TrainerController._reset_env": {
"total": 3.799978363999969,
"count": 1,
"self": 3.799978363999969
},
"TrainerController.advance": {
"total": 450.98297227600233,
"count": 18202,
"self": 0.2679865059971007,
"children": {
"env_step": {
"total": 450.7149857700052,
"count": 18202,
"self": 319.1889454679992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.26446446400138,
"count": 18202,
"self": 1.5003559839979062,
"children": {
"TorchPolicy.evaluate": {
"total": 129.76410848000347,
"count": 18202,
"self": 29.02481575099091,
"children": {
"TorchPolicy.sample_actions": {
"total": 100.73929272901256,
"count": 18202,
"self": 100.73929272901256
}
}
}
}
},
"workers": {
"total": 0.26157583800466,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.8445646920028,
"count": 18202,
"is_parallel": true,
"self": 214.76916125700387,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004772009000021171,
"count": 1,
"is_parallel": true,
"self": 0.003273396000224693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001498612999796478,
"count": 10,
"is_parallel": true,
"self": 0.001498612999796478
}
}
},
"UnityEnvironment.step": {
"total": 0.050304845000027854,
"count": 1,
"is_parallel": true,
"self": 0.0005165150000721042,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000311156000009305,
"count": 1,
"is_parallel": true,
"self": 0.000311156000009305
},
"communicator.exchange": {
"total": 0.04756953699995847,
"count": 1,
"is_parallel": true,
"self": 0.04756953699995847
},
"steps_from_proto": {
"total": 0.0019076369999879716,
"count": 1,
"is_parallel": true,
"self": 0.00041791499990040393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014897220000875677,
"count": 10,
"is_parallel": true,
"self": 0.0014897220000875677
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.07540343499892,
"count": 18201,
"is_parallel": true,
"self": 9.619331255000588,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.264166866000835,
"count": 18201,
"is_parallel": true,
"self": 5.264166866000835
},
"communicator.exchange": {
"total": 192.3733527930006,
"count": 18201,
"is_parallel": true,
"self": 192.3733527930006
},
"steps_from_proto": {
"total": 31.81855252099689,
"count": 18201,
"is_parallel": true,
"self": 6.9745840280018,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.84396849299509,
"count": 182010,
"is_parallel": true,
"self": 24.84396849299509
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001462480000782307,
"count": 1,
"self": 0.0001462480000782307,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.7022667999642,
"count": 401202,
"is_parallel": true,
"self": 10.307971206967238,
"children": {
"process_trajectory": {
"total": 252.1411777679972,
"count": 401202,
"is_parallel": true,
"self": 251.09543606599732,
"children": {
"RLTrainer._checkpoint": {
"total": 1.045741701999873,
"count": 4,
"is_parallel": true,
"self": 1.045741701999873
}
}
},
"_update_policy": {
"total": 185.25311782499978,
"count": 90,
"is_parallel": true,
"self": 72.3952630259987,
"children": {
"TorchPPOOptimizer.update": {
"total": 112.85785479900107,
"count": 4584,
"is_parallel": true,
"self": 112.85785479900107
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11899813200000153,
"count": 1,
"self": 0.000860475000081351,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11813765699992018,
"count": 1,
"self": 0.11813765699992018
}
}
}
}
}
}
}