MalyO2's picture
First Push
709c5fa verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0330702066421509,
"min": 1.0317896604537964,
"max": 2.8766300678253174,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9886.4814453125,
"min": 9886.4814453125,
"max": 29554.49609375,
"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": 11.979909896850586,
"min": 0.3826034367084503,
"max": 11.979909896850586,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2336.08251953125,
"min": 74.22506713867188,
"max": 2425.8291015625,
"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": 0.06719930537294613,
"min": 0.062401021625755324,
"max": 0.08114699743572262,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26879722149178453,
"min": 0.26090638227220087,
"max": 0.3839573659397679,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19065257035853234,
"min": 0.11740876022525423,
"max": 0.2827732439572905,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7626102814341293,
"min": 0.46963504090101693,
"max": 1.392621084171183,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.106097298000005e-06,
"min": 8.106097298000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.242438919200002e-05,
"min": 3.242438919200002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10270200000000002,
"min": 0.10270200000000002,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41080800000000006,
"min": 0.41080800000000006,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014482980000000007,
"min": 0.00014482980000000007,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005793192000000003,
"min": 0.0005793192000000003,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.613636363636363,
"min": 3.022727272727273,
"max": 23.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1039.0,
"min": 133.0,
"max": 1304.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.613636363636363,
"min": 3.022727272727273,
"max": 23.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1039.0,
"min": 133.0,
"max": 1304.0,
"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": "1728395842",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728396463"
},
"total": 620.8546605059998,
"count": 1,
"self": 0.6384492629997567,
"children": {
"run_training.setup": {
"total": 0.07605513400017117,
"count": 1,
"self": 0.07605513400017117
},
"TrainerController.start_learning": {
"total": 620.1401561089999,
"count": 1,
"self": 0.8475402360095359,
"children": {
"TrainerController._reset_env": {
"total": 3.5212067929999193,
"count": 1,
"self": 3.5212067929999193
},
"TrainerController.advance": {
"total": 615.6819638739903,
"count": 18202,
"self": 0.4400479689761596,
"children": {
"env_step": {
"total": 615.2419159050141,
"count": 18202,
"self": 471.4198327470194,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.37020815099436,
"count": 18202,
"self": 2.461876773955055,
"children": {
"TorchPolicy.evaluate": {
"total": 140.9083313770393,
"count": 18202,
"self": 140.9083313770393
}
}
},
"workers": {
"total": 0.45187500700035343,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 618.2281564110183,
"count": 18202,
"is_parallel": true,
"self": 294.49471070702907,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0035808840000299824,
"count": 1,
"is_parallel": true,
"self": 0.0011897040001258574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002391179999904125,
"count": 10,
"is_parallel": true,
"self": 0.002391179999904125
}
}
},
"UnityEnvironment.step": {
"total": 0.12354841699993813,
"count": 1,
"is_parallel": true,
"self": 0.001612734000218552,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007052879998354911,
"count": 1,
"is_parallel": true,
"self": 0.0007052879998354911
},
"communicator.exchange": {
"total": 0.1162262099999225,
"count": 1,
"is_parallel": true,
"self": 0.1162262099999225
},
"steps_from_proto": {
"total": 0.005004184999961581,
"count": 1,
"is_parallel": true,
"self": 0.0005034309997427044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004500754000218876,
"count": 10,
"is_parallel": true,
"self": 0.004500754000218876
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 323.7334457039892,
"count": 18201,
"is_parallel": true,
"self": 15.80642756897987,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.767527781994431,
"count": 18201,
"is_parallel": true,
"self": 7.767527781994431
},
"communicator.exchange": {
"total": 254.4872219919812,
"count": 18201,
"is_parallel": true,
"self": 254.4872219919812
},
"steps_from_proto": {
"total": 45.67226836103373,
"count": 18201,
"is_parallel": true,
"self": 9.1989461269593,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.47332223407443,
"count": 182010,
"is_parallel": true,
"self": 36.47332223407443
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0004312360001677007,
"count": 1,
"self": 0.0004312360001677007,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 608.2537871458437,
"count": 818995,
"is_parallel": true,
"self": 19.22768101006318,
"children": {
"process_trajectory": {
"total": 330.72314858378127,
"count": 818995,
"is_parallel": true,
"self": 329.25518976278113,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4679588210001384,
"count": 4,
"is_parallel": true,
"self": 1.4679588210001384
}
}
},
"_update_policy": {
"total": 258.30295755199927,
"count": 90,
"is_parallel": true,
"self": 72.23976620899452,
"children": {
"TorchPPOOptimizer.update": {
"total": 186.06319134300475,
"count": 4584,
"is_parallel": true,
"self": 186.06319134300475
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08901396999999633,
"count": 1,
"self": 0.0012731490000987833,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08774082099989755,
"count": 1,
"self": 0.08774082099989755
}
}
}
}
}
}
}