Dash10107's picture
First Push
03a9805 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8001843094825745,
"min": 0.7810786366462708,
"max": 2.852370262145996,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7604.95166015625,
"min": 7584.771484375,
"max": 29116.99609375,
"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": 12.926309585571289,
"min": 0.35359281301498413,
"max": 12.967205047607422,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.63037109375,
"min": 68.59700775146484,
"max": 2658.277099609375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07279257838201694,
"min": 0.06216460053909424,
"max": 0.07464350587688386,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29117031352806777,
"min": 0.24865840215637697,
"max": 0.37321752938441927,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19421470084903286,
"min": 0.14227578715608435,
"max": 0.2971154254148988,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7768588033961314,
"min": 0.5691031486243374,
"max": 1.4169321887049018,
"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": 3.659090909090909,
"max": 25.89090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 161.0,
"max": 1424.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 3.659090909090909,
"max": 25.89090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 161.0,
"max": 1424.0,
"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": "1775405464",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/usr/local/envs/mlagents_env/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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1775405935"
},
"total": 470.5865948840001,
"count": 1,
"self": 0.4325928540001769,
"children": {
"run_training.setup": {
"total": 0.024757393999607302,
"count": 1,
"self": 0.024757393999607302
},
"TrainerController.start_learning": {
"total": 470.1292446360003,
"count": 1,
"self": 0.39135168393477215,
"children": {
"TrainerController._reset_env": {
"total": 3.2286389789996974,
"count": 1,
"self": 3.2286389789996974
},
"TrainerController.advance": {
"total": 466.42796577106583,
"count": 18192,
"self": 0.3970598829419032,
"children": {
"env_step": {
"total": 338.68519418206415,
"count": 18192,
"self": 260.3526380600615,
"children": {
"SubprocessEnvManager._take_step": {
"total": 78.10144090098493,
"count": 18192,
"self": 1.3388363329222557,
"children": {
"TorchPolicy.evaluate": {
"total": 76.76260456806267,
"count": 18192,
"self": 76.76260456806267
}
}
},
"workers": {
"total": 0.23111522101771698,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.1163399180705,
"count": 18192,
"is_parallel": true,
"self": 239.91233963010654,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005170728000848612,
"count": 1,
"is_parallel": true,
"self": 0.003718176002621476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014525519982271362,
"count": 10,
"is_parallel": true,
"self": 0.0014525519982271362
}
}
},
"UnityEnvironment.step": {
"total": 0.07548064799993881,
"count": 1,
"is_parallel": true,
"self": 0.0016334279998773127,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003909050001311698,
"count": 1,
"is_parallel": true,
"self": 0.0003909050001311698
},
"communicator.exchange": {
"total": 0.06939225899986923,
"count": 1,
"is_parallel": true,
"self": 0.06939225899986923
},
"steps_from_proto": {
"total": 0.0040640560000611,
"count": 1,
"is_parallel": true,
"self": 0.00040516800072509795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0036588879993360024,
"count": 10,
"is_parallel": true,
"self": 0.0036588879993360024
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.20400028796394,
"count": 18191,
"is_parallel": true,
"self": 10.235004658947219,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.009571189944836,
"count": 18191,
"is_parallel": true,
"self": 6.009571189944836
},
"communicator.exchange": {
"total": 173.59037900203202,
"count": 18191,
"is_parallel": true,
"self": 173.59037900203202
},
"steps_from_proto": {
"total": 38.36904543703986,
"count": 18191,
"is_parallel": true,
"self": 7.034971935117028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.33407350192283,
"count": 181910,
"is_parallel": true,
"self": 31.33407350192283
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.34571170605977,
"count": 18192,
"self": 0.4893014881417912,
"children": {
"process_trajectory": {
"total": 28.142108856912273,
"count": 18192,
"self": 27.693001023912984,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4491078329992888,
"count": 4,
"self": 0.4491078329992888
}
}
},
"_update_policy": {
"total": 98.71430136100571,
"count": 90,
"self": 38.94215977598742,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.77214158501829,
"count": 4587,
"self": 59.77214158501829
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.45900002180133e-06,
"count": 1,
"self": 5.45900002180133e-06
},
"TrainerController._save_models": {
"total": 0.08128274299997429,
"count": 1,
"self": 0.0007735229992249515,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08050922000074934,
"count": 1,
"self": 0.08050922000074934
}
}
}
}
}
}
}