ynsturgt's picture
First Push
dfd936c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8312729001045227,
"min": 0.8312729001045227,
"max": 2.823068857192993,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7900.41748046875,
"min": 7900.41748046875,
"max": 28817.88671875,
"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": 12.786881446838379,
"min": 0.531845211982727,
"max": 12.786881446838379,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.44189453125,
"min": 103.17797088623047,
"max": 2581.691650390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06911971299054773,
"min": 0.06051951498697833,
"max": 0.07418276789123375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2764788519621909,
"min": 0.24207805994791332,
"max": 0.3636397253961631,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20772786431160628,
"min": 0.13539617824569053,
"max": 0.27278919623178594,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8309114572464251,
"min": 0.5415847129827621,
"max": 1.3639459811589296,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.59090909090909,
"min": 3.7045454545454546,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 163.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 3.7045454545454546,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 163.0,
"max": 1399.0,
"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": "1741959420",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741959845"
},
"total": 425.1935505240001,
"count": 1,
"self": 0.3868584520001832,
"children": {
"run_training.setup": {
"total": 0.022759420999932445,
"count": 1,
"self": 0.022759420999932445
},
"TrainerController.start_learning": {
"total": 424.783932651,
"count": 1,
"self": 0.32606648499370294,
"children": {
"TrainerController._reset_env": {
"total": 3.245889118999912,
"count": 1,
"self": 3.245889118999912
},
"TrainerController.advance": {
"total": 421.10807140900647,
"count": 18192,
"self": 0.3439191010061222,
"children": {
"env_step": {
"total": 294.98492053600376,
"count": 18192,
"self": 223.3704805289966,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.41642050900793,
"count": 18192,
"self": 1.259825247999288,
"children": {
"TorchPolicy.evaluate": {
"total": 70.15659526100865,
"count": 18192,
"self": 70.15659526100865
}
}
},
"workers": {
"total": 0.19801949799921204,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.3555390779986,
"count": 18192,
"is_parallel": true,
"self": 227.4060651599989,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005787284000007276,
"count": 1,
"is_parallel": true,
"self": 0.004130730999918342,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001656553000088934,
"count": 10,
"is_parallel": true,
"self": 0.001656553000088934
}
}
},
"UnityEnvironment.step": {
"total": 0.06611075100011021,
"count": 1,
"is_parallel": true,
"self": 0.00871274800010724,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037027199994099647,
"count": 1,
"is_parallel": true,
"self": 0.00037027199994099647
},
"communicator.exchange": {
"total": 0.05477934500004267,
"count": 1,
"is_parallel": true,
"self": 0.05477934500004267
},
"steps_from_proto": {
"total": 0.002248386000019309,
"count": 1,
"is_parallel": true,
"self": 0.0004158119998010079,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001832574000218301,
"count": 10,
"is_parallel": true,
"self": 0.001832574000218301
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 195.94947391799974,
"count": 18191,
"is_parallel": true,
"self": 9.492351698996913,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.202991346003955,
"count": 18191,
"is_parallel": true,
"self": 5.202991346003955
},
"communicator.exchange": {
"total": 150.15065282000558,
"count": 18191,
"is_parallel": true,
"self": 150.15065282000558
},
"steps_from_proto": {
"total": 31.103478052993296,
"count": 18191,
"is_parallel": true,
"self": 5.541127937995611,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.562350114997685,
"count": 181910,
"is_parallel": true,
"self": 25.562350114997685
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.77923177199659,
"count": 18192,
"self": 0.3862563009980704,
"children": {
"process_trajectory": {
"total": 27.378651305998574,
"count": 18192,
"self": 26.884615661998396,
"children": {
"RLTrainer._checkpoint": {
"total": 0.49403564400017785,
"count": 4,
"self": 0.49403564400017785
}
}
},
"_update_policy": {
"total": 98.01432416499995,
"count": 90,
"self": 38.18094667199978,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.83337749300017,
"count": 4587,
"self": 59.83337749300017
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.78000002760382e-07,
"count": 1,
"self": 9.78000002760382e-07
},
"TrainerController._save_models": {
"total": 0.10390465999989829,
"count": 1,
"self": 0.0010756719998425979,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10282898800005569,
"count": 1,
"self": 0.10282898800005569
}
}
}
}
}
}
}