mandell's picture
First Push
4df3f5c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7927649021148682,
"min": 0.7927649021148682,
"max": 2.851468324661255,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7534.4375,
"min": 7534.4375,
"max": 29107.7890625,
"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": 13.059830665588379,
"min": 0.40170276165008545,
"max": 13.059830665588379,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2546.6669921875,
"min": 77.93033599853516,
"max": 2626.8408203125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07455100010477456,
"min": 0.059628715476434335,
"max": 0.07455100010477456,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2982040004190982,
"min": 0.23851486190573734,
"max": 0.35954754940329997,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1866479035759089,
"min": 0.10852093301375634,
"max": 0.2776211366933935,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7465916143036356,
"min": 0.4340837320550254,
"max": 1.3881056834669674,
"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": 25.75,
"min": 3.227272727272727,
"max": 25.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 142.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 3.227272727272727,
"max": 25.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 142.0,
"max": 1413.0,
"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": "1749369732",
"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": "1749370183"
},
"total": 450.886869746,
"count": 1,
"self": 0.4389900650000982,
"children": {
"run_training.setup": {
"total": 0.022639573999867935,
"count": 1,
"self": 0.022639573999867935
},
"TrainerController.start_learning": {
"total": 450.42524010700004,
"count": 1,
"self": 0.3948275780003314,
"children": {
"TrainerController._reset_env": {
"total": 3.1390415319999647,
"count": 1,
"self": 3.1390415319999647
},
"TrainerController.advance": {
"total": 446.8084048349997,
"count": 18192,
"self": 0.4223998239831417,
"children": {
"env_step": {
"total": 319.20639885600986,
"count": 18192,
"self": 241.54091029000642,
"children": {
"SubprocessEnvManager._take_step": {
"total": 77.43323437900744,
"count": 18192,
"self": 1.3801611809924452,
"children": {
"TorchPolicy.evaluate": {
"total": 76.053073198015,
"count": 18192,
"self": 76.053073198015
}
}
},
"workers": {
"total": 0.23225418699598777,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 448.92054933000804,
"count": 18192,
"is_parallel": true,
"self": 237.54369256499035,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005432604999896284,
"count": 1,
"is_parallel": true,
"self": 0.0038316009995469358,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016010040003493486,
"count": 10,
"is_parallel": true,
"self": 0.0016010040003493486
}
}
},
"UnityEnvironment.step": {
"total": 0.0374686320001274,
"count": 1,
"is_parallel": true,
"self": 0.0006961780002257001,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040101299987327366,
"count": 1,
"is_parallel": true,
"self": 0.00040101299987327366
},
"communicator.exchange": {
"total": 0.034459083000001556,
"count": 1,
"is_parallel": true,
"self": 0.034459083000001556
},
"steps_from_proto": {
"total": 0.0019123580000268703,
"count": 1,
"is_parallel": true,
"self": 0.000367949999827033,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015444080001998373,
"count": 10,
"is_parallel": true,
"self": 0.0015444080001998373
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.3768567650177,
"count": 18191,
"is_parallel": true,
"self": 10.24788091402911,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.8232667469867465,
"count": 18191,
"is_parallel": true,
"self": 5.8232667469867465
},
"communicator.exchange": {
"total": 161.63376393200838,
"count": 18191,
"is_parallel": true,
"self": 161.63376393200838
},
"steps_from_proto": {
"total": 33.67194517199346,
"count": 18191,
"is_parallel": true,
"self": 6.1139771550333535,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.557968016960103,
"count": 181910,
"is_parallel": true,
"self": 27.557968016960103
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.1796061550067,
"count": 18192,
"self": 0.4844198980126748,
"children": {
"process_trajectory": {
"total": 28.76411232799478,
"count": 18192,
"self": 28.305929502995014,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45818282499976704,
"count": 4,
"self": 0.45818282499976704
}
}
},
"_update_policy": {
"total": 97.93107392899924,
"count": 90,
"self": 39.82047924199833,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.11059468700091,
"count": 4587,
"self": 58.11059468700091
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.150001005764352e-07,
"count": 1,
"self": 9.150001005764352e-07
},
"TrainerController._save_models": {
"total": 0.08296524699994734,
"count": 1,
"self": 0.0008401180000419117,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08212512899990543,
"count": 1,
"self": 0.08212512899990543
}
}
}
}
}
}
}