pdx97's picture
First Push
a8a33a2 verified
raw
history blame
18.4 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.2308859825134277,
"min": 2.2308859825134277,
"max": 2.829777240753174,
"count": 4
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 111287.75,
"min": 111287.75,
"max": 142937.703125,
"count": 4
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 49936.0,
"max": 199984.0,
"count": 4
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 49936.0,
"max": 199984.0,
"count": 4
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 5.097272872924805,
"min": 0.3275330066680908,
"max": 5.097272872924805,
"count": 4
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 5061.591796875,
"min": 324.9127502441406,
"max": 5061.591796875,
"count": 4
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 4
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 50347.0,
"min": 48158.0,
"max": 50347.0,
"count": 4
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 14.363636363636363,
"min": 4.776859504132231,
"max": 14.363636363636363,
"count": 4
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 3476.0,
"min": 1156.0,
"max": 3476.0,
"count": 4
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 14.363636363636363,
"min": 4.776859504132231,
"max": 14.363636363636363,
"count": 4
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 3476.0,
"min": 1156.0,
"max": 3476.0,
"count": 4
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06886937141266089,
"min": 0.06852080622246946,
"max": 0.07431110412473704,
"count": 4
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3443468570633045,
"min": 0.29724441649894817,
"max": 0.34791849345418213,
"count": 4
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2623727392193441,
"min": 0.14703906745668135,
"max": 0.2623727392193441,
"count": 4
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.3118636960967207,
"min": 0.5881562698267254,
"max": 1.3118636960967207,
"count": 4
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.3201688932800005e-05,
"min": 3.3201688932800005e-05,
"max": 0.0002604660131779999,
"count": 4
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00016600844466400003,
"min": 0.00016600844466400003,
"max": 0.0010418640527119997,
"count": 4
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1110672,
"min": 0.1110672,
"max": 0.18682200000000002,
"count": 4
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.555336,
"min": 0.555336,
"max": 0.8167200000000001,
"count": 4
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0005622532800000002,
"min": 0.0005622532800000002,
"max": 0.0043424178,
"count": 4
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0028112664000000008,
"min": 0.0028112664000000008,
"max": 0.0173696712,
"count": 4
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1713157526",
"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 --force",
"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": "1713158086"
},
"total": 560.2416673719999,
"count": 1,
"self": 0.4911368580000044,
"children": {
"run_training.setup": {
"total": 0.05985040999996727,
"count": 1,
"self": 0.05985040999996727
},
"TrainerController.start_learning": {
"total": 559.690680104,
"count": 1,
"self": 0.7603092410182626,
"children": {
"TrainerController._reset_env": {
"total": 2.93413624599998,
"count": 1,
"self": 2.93413624599998
},
"TrainerController.advance": {
"total": 555.8957552969817,
"count": 18203,
"self": 0.3446716199727007,
"children": {
"env_step": {
"total": 555.551083677009,
"count": 18203,
"self": 390.30330310500085,
"children": {
"SubprocessEnvManager._take_step": {
"total": 164.86987684900078,
"count": 18203,
"self": 1.8076509829934366,
"children": {
"TorchPolicy.evaluate": {
"total": 163.06222586600734,
"count": 18203,
"self": 163.06222586600734
}
}
},
"workers": {
"total": 0.3779037230074209,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 558.2016177250031,
"count": 18203,
"is_parallel": true,
"self": 285.8535218200012,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008546129000023939,
"count": 1,
"is_parallel": true,
"self": 0.0008938590000298063,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.007652269999994132,
"count": 10,
"is_parallel": true,
"self": 0.007652269999994132
}
}
},
"UnityEnvironment.step": {
"total": 0.04396688600002108,
"count": 1,
"is_parallel": true,
"self": 0.000813094999898567,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004546980001123302,
"count": 1,
"is_parallel": true,
"self": 0.0004546980001123302
},
"communicator.exchange": {
"total": 0.039941198000065015,
"count": 1,
"is_parallel": true,
"self": 0.039941198000065015
},
"steps_from_proto": {
"total": 0.002757894999945165,
"count": 1,
"is_parallel": true,
"self": 0.0005295849999811253,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00222830999996404,
"count": 10,
"is_parallel": true,
"self": 0.00222830999996404
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 272.34809590500186,
"count": 18202,
"is_parallel": true,
"self": 12.49743778398522,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.599381185008269,
"count": 18202,
"is_parallel": true,
"self": 6.599381185008269
},
"communicator.exchange": {
"total": 211.46358570101472,
"count": 18202,
"is_parallel": true,
"self": 211.46358570101472
},
"steps_from_proto": {
"total": 41.787691234993645,
"count": 18202,
"is_parallel": true,
"self": 7.96744859801845,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.820242636975195,
"count": 182020,
"is_parallel": true,
"self": 33.820242636975195
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00024052399999163754,
"count": 1,
"self": 0.00024052399999163754,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 545.2370239150921,
"count": 1118278,
"is_parallel": true,
"self": 26.113697430140746,
"children": {
"process_trajectory": {
"total": 385.2787320609509,
"count": 1118278,
"is_parallel": true,
"self": 384.7763065409508,
"children": {
"RLTrainer._checkpoint": {
"total": 0.502425520000088,
"count": 4,
"is_parallel": true,
"self": 0.502425520000088
}
}
},
"_update_policy": {
"total": 133.84459442400043,
"count": 19,
"is_parallel": true,
"self": 49.236771409997004,
"children": {
"TorchPPOOptimizer.update": {
"total": 84.60782301400343,
"count": 4632,
"is_parallel": true,
"self": 84.60782301400343
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10023879599998509,
"count": 1,
"self": 0.00099384000009195,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09924495599989314,
"count": 1,
"self": 0.09924495599989314
}
}
}
}
}
}
}