unit5_coursrl / run_logs /timers.json
hlabedade's picture
correction
b764a48
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0139832496643066,
"min": 1.0139832496643066,
"max": 2.8511552810668945,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9714.9736328125,
"min": 9714.9736328125,
"max": 29261.40625,
"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": 11.640793800354004,
"min": 0.3280394673347473,
"max": 11.640793800354004,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2269.954833984375,
"min": 63.63965606689453,
"max": 2327.32568359375,
"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": 0.06915216114986619,
"min": 0.06216770397740594,
"max": 0.07481453355159792,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27660864459946477,
"min": 0.24867081590962375,
"max": 0.37407266775798964,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20661227321069617,
"min": 0.13202306001182354,
"max": 0.2660935948438504,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8264490928427847,
"min": 0.5280922400472942,
"max": 1.3260735384389466,
"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": 23.545454545454547,
"min": 3.8181818181818183,
"max": 23.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1036.0,
"min": 168.0,
"max": 1251.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.545454545454547,
"min": 3.8181818181818183,
"max": 23.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1036.0,
"min": 168.0,
"max": 1251.0,
"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": "1700146703",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700147325"
},
"total": 621.7993662199997,
"count": 1,
"self": 0.4966174369997134,
"children": {
"run_training.setup": {
"total": 0.0666884420002134,
"count": 1,
"self": 0.0666884420002134
},
"TrainerController.start_learning": {
"total": 621.2360603409998,
"count": 1,
"self": 0.901424472018789,
"children": {
"TrainerController._reset_env": {
"total": 1.7918718509999962,
"count": 1,
"self": 1.7918718509999962
},
"TrainerController.advance": {
"total": 618.447867281981,
"count": 18202,
"self": 0.44311731101151963,
"children": {
"env_step": {
"total": 618.0047499709694,
"count": 18202,
"self": 485.7532575089049,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.8181831750312,
"count": 18202,
"self": 2.384890469012589,
"children": {
"TorchPolicy.evaluate": {
"total": 129.43329270601862,
"count": 18202,
"self": 129.43329270601862
}
}
},
"workers": {
"total": 0.43330928703335303,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 619.0002713279987,
"count": 18202,
"is_parallel": true,
"self": 281.79653253198376,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007551805999810313,
"count": 1,
"is_parallel": true,
"self": 0.005585583000538463,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019662229992718494,
"count": 10,
"is_parallel": true,
"self": 0.0019662229992718494
}
}
},
"UnityEnvironment.step": {
"total": 0.04398261799997272,
"count": 1,
"is_parallel": true,
"self": 0.0007217799998215924,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004538650000540656,
"count": 1,
"is_parallel": true,
"self": 0.0004538650000540656
},
"communicator.exchange": {
"total": 0.03924568699994779,
"count": 1,
"is_parallel": true,
"self": 0.03924568699994779
},
"steps_from_proto": {
"total": 0.0035612860001492663,
"count": 1,
"is_parallel": true,
"self": 0.0015867300003264972,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001974555999822769,
"count": 10,
"is_parallel": true,
"self": 0.001974555999822769
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 337.20373879601493,
"count": 18201,
"is_parallel": true,
"self": 14.618597974999375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.548720368014983,
"count": 18201,
"is_parallel": true,
"self": 7.548720368014983
},
"communicator.exchange": {
"total": 268.902900872014,
"count": 18201,
"is_parallel": true,
"self": 268.902900872014
},
"steps_from_proto": {
"total": 46.13351958098656,
"count": 18201,
"is_parallel": true,
"self": 9.179475966996051,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.95404361399051,
"count": 182010,
"is_parallel": true,
"self": 36.95404361399051
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014071199984755367,
"count": 1,
"self": 0.00014071199984755367,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 612.9745755809781,
"count": 636550,
"is_parallel": true,
"self": 14.9998624259174,
"children": {
"process_trajectory": {
"total": 335.34647999806066,
"count": 636550,
"is_parallel": true,
"self": 333.97612937706117,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3703506209994885,
"count": 4,
"is_parallel": true,
"self": 1.3703506209994885
}
}
},
"_update_policy": {
"total": 262.62823315700007,
"count": 90,
"is_parallel": true,
"self": 81.60705460899771,
"children": {
"TorchPPOOptimizer.update": {
"total": 181.02117854800235,
"count": 4587,
"is_parallel": true,
"self": 181.02117854800235
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09475602400016214,
"count": 1,
"self": 0.001057013000263396,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09369901099989875,
"count": 1,
"self": 0.09369901099989875
}
}
}
}
}
}
}