Sandf1sh's picture
First Push
d449761 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8179445862770081,
"min": 0.7870913147926331,
"max": 2.8336896896362305,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7773.7451171875,
"min": 7773.7451171875,
"max": 28926.3046875,
"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": 13.041571617126465,
"min": 0.37682342529296875,
"max": 13.041571617126465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2543.1064453125,
"min": 73.10374450683594,
"max": 2650.588134765625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06971713855864436,
"min": 0.06021542503371094,
"max": 0.0731742394216103,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27886855423457746,
"min": 0.24086170013484376,
"max": 0.35867307699877793,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1970739642925122,
"min": 0.10820385783353784,
"max": 0.2949990562364167,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7882958571700488,
"min": 0.43281543133415135,
"max": 1.4749952811820835,
"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": 3.159090909090909,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 139.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 3.159090909090909,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 139.0,
"max": 1416.0,
"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": "1751282214",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751282628"
},
"total": 414.27562579100004,
"count": 1,
"self": 0.38643598299995574,
"children": {
"run_training.setup": {
"total": 0.03451621800002158,
"count": 1,
"self": 0.03451621800002158
},
"TrainerController.start_learning": {
"total": 413.85467359000006,
"count": 1,
"self": 0.31900986301195644,
"children": {
"TrainerController._reset_env": {
"total": 2.99698885600003,
"count": 1,
"self": 2.99698885600003
},
"TrainerController.advance": {
"total": 410.46155396798815,
"count": 18192,
"self": 0.3531949899937672,
"children": {
"env_step": {
"total": 294.0391984699929,
"count": 18192,
"self": 226.15768650498853,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.68452485599289,
"count": 18192,
"self": 1.213782319981192,
"children": {
"TorchPolicy.evaluate": {
"total": 66.4707425360117,
"count": 18192,
"self": 66.4707425360117
}
}
},
"workers": {
"total": 0.19698710901150207,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.47120184600453,
"count": 18192,
"is_parallel": true,
"self": 213.54521768000438,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004795535999960521,
"count": 1,
"is_parallel": true,
"self": 0.003312863000132893,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014826729998276278,
"count": 10,
"is_parallel": true,
"self": 0.0014826729998276278
}
}
},
"UnityEnvironment.step": {
"total": 0.034757775000002766,
"count": 1,
"is_parallel": true,
"self": 0.0005738369999335191,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004010410000319098,
"count": 1,
"is_parallel": true,
"self": 0.0004010410000319098
},
"communicator.exchange": {
"total": 0.031713005000028716,
"count": 1,
"is_parallel": true,
"self": 0.031713005000028716
},
"steps_from_proto": {
"total": 0.002069892000008622,
"count": 1,
"is_parallel": true,
"self": 0.0005857390000301166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014841529999785052,
"count": 10,
"is_parallel": true,
"self": 0.0014841529999785052
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 198.92598416600015,
"count": 18191,
"is_parallel": true,
"self": 9.794114729991747,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.322943436002561,
"count": 18191,
"is_parallel": true,
"self": 5.322943436002561
},
"communicator.exchange": {
"total": 152.53835955200952,
"count": 18191,
"is_parallel": true,
"self": 152.53835955200952
},
"steps_from_proto": {
"total": 31.270566447996316,
"count": 18191,
"is_parallel": true,
"self": 5.587790800007042,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.682775647989274,
"count": 181910,
"is_parallel": true,
"self": 25.682775647989274
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.06916050800146,
"count": 18192,
"self": 0.39425968100192677,
"children": {
"process_trajectory": {
"total": 25.79600074599898,
"count": 18192,
"self": 25.400508108998906,
"children": {
"RLTrainer._checkpoint": {
"total": 0.39549263700007486,
"count": 4,
"self": 0.39549263700007486
}
}
},
"_update_policy": {
"total": 89.87890008100055,
"count": 90,
"self": 37.01558674000273,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.86331334099782,
"count": 4587,
"self": 52.86331334099782
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.670000054029515e-07,
"count": 1,
"self": 9.670000054029515e-07
},
"TrainerController._save_models": {
"total": 0.07711993599991729,
"count": 1,
"self": 0.0010286959998211387,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07609124000009615,
"count": 1,
"self": 0.07609124000009615
}
}
}
}
}
}
}