chirbard's picture
First Push
3e77564 verified
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0067580938339233,
"min": 1.0067580938339233,
"max": 2.874189615249634,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9678.97265625,
"min": 9678.97265625,
"max": 29529.423828125,
"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": 12.819340705871582,
"min": 0.33539775013923645,
"max": 12.824774742126465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2499.771484375,
"min": 65.0671615600586,
"max": 2609.42919921875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07429816948826876,
"min": 0.06175319821526429,
"max": 0.07429816948826876,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.297192677953075,
"min": 0.24701279286105715,
"max": 0.35531605310582864,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19709242902257865,
"min": 0.11832383954577952,
"max": 0.2839381074642434,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7883697160903146,
"min": 0.4732953581831181,
"max": 1.3797803302021587,
"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": 25.295454545454547,
"min": 3.1818181818181817,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 140.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.1818181818181817,
"max": 25.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 140.0,
"max": 1413.0,
"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": "1714294416",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714295059"
},
"total": 642.377410703,
"count": 1,
"self": 0.21941505200004485,
"children": {
"run_training.setup": {
"total": 0.029690779000020484,
"count": 1,
"self": 0.029690779000020484
},
"TrainerController.start_learning": {
"total": 642.128304872,
"count": 1,
"self": 0.37253845504437777,
"children": {
"TrainerController._reset_env": {
"total": 4.102196714999991,
"count": 1,
"self": 4.102196714999991
},
"TrainerController.advance": {
"total": 637.4806205119555,
"count": 18206,
"self": 0.1647147609453441,
"children": {
"env_step": {
"total": 637.3159057510102,
"count": 18206,
"self": 253.42344066901035,
"children": {
"SubprocessEnvManager._take_step": {
"total": 383.7178334890111,
"count": 18206,
"self": 0.9027316990076315,
"children": {
"TorchPolicy.evaluate": {
"total": 382.8151017900035,
"count": 18206,
"self": 382.8151017900035
}
}
},
"workers": {
"total": 0.17463159298870323,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 641.2974763860074,
"count": 18206,
"is_parallel": true,
"self": 473.0435515430021,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0015390730000035546,
"count": 1,
"is_parallel": true,
"self": 0.00041842400014502346,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011206489998585312,
"count": 10,
"is_parallel": true,
"self": 0.0011206489998585312
}
}
},
"UnityEnvironment.step": {
"total": 0.017933181999978842,
"count": 1,
"is_parallel": true,
"self": 0.00025460299991664215,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00016129200002978905,
"count": 1,
"is_parallel": true,
"self": 0.00016129200002978905
},
"communicator.exchange": {
"total": 0.016930290999994213,
"count": 1,
"is_parallel": true,
"self": 0.016930290999994213
},
"steps_from_proto": {
"total": 0.000586996000038198,
"count": 1,
"is_parallel": true,
"self": 0.0001373320000084277,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00044966400002977025,
"count": 10,
"is_parallel": true,
"self": 0.00044966400002977025
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 168.25392484300528,
"count": 18205,
"is_parallel": true,
"self": 3.7489551640104537,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.1647984059962937,
"count": 18205,
"is_parallel": true,
"self": 2.1647984059962937
},
"communicator.exchange": {
"total": 152.13003654499926,
"count": 18205,
"is_parallel": true,
"self": 152.13003654499926
},
"steps_from_proto": {
"total": 10.210134727999275,
"count": 18205,
"is_parallel": true,
"self": 2.3469098419751617,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.863224886024113,
"count": 182050,
"is_parallel": true,
"self": 7.863224886024113
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.017000002131681e-05,
"count": 1,
"self": 9.017000002131681e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 634.8592827860347,
"count": 530686,
"is_parallel": true,
"self": 6.598989058971824,
"children": {
"process_trajectory": {
"total": 281.78387542506255,
"count": 530686,
"is_parallel": true,
"self": 281.0188311150624,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7650443100001212,
"count": 4,
"is_parallel": true,
"self": 0.7650443100001212
}
}
},
"_update_policy": {
"total": 346.4764183020003,
"count": 90,
"is_parallel": true,
"self": 25.188981678000573,
"children": {
"TorchPPOOptimizer.update": {
"total": 321.2874366239997,
"count": 4587,
"is_parallel": true,
"self": 321.2874366239997
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.17285902000003261,
"count": 1,
"self": 0.00042507900002419774,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17243394100000842,
"count": 1,
"self": 0.17243394100000842
}
}
}
}
}
}
}