sanjay-906's picture
First Push
a928e14 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.70677649974823,
"min": 0.70677649974823,
"max": 2.842465400695801,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6717.2041015625,
"min": 6717.2041015625,
"max": 29015.88671875,
"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": 12.790069580078125,
"min": 0.3699909746646881,
"max": 12.818243980407715,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2494.0634765625,
"min": 71.77825164794922,
"max": 2610.8623046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06609601649346158,
"min": 0.06356930125723154,
"max": 0.07642771844523083,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26438406597384634,
"min": 0.25427720502892615,
"max": 0.35802639254018453,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1902652094323261,
"min": 0.13746315255925498,
"max": 0.2941388748586178,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7610608377293044,
"min": 0.5498526102370199,
"max": 1.3988473803973667,
"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": 25.272727272727273,
"min": 3.772727272727273,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 166.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.772727272727273,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 166.0,
"max": 1379.0,
"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": "1739075961",
"python_version": "3.10.12 (main, Jan 17 2025, 14:35:34) [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=SnowballTarget1 --no-graphics --force",
"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": "1739076402"
},
"total": 440.92710009999996,
"count": 1,
"self": 0.44406399000001784,
"children": {
"run_training.setup": {
"total": 0.018899142000009306,
"count": 1,
"self": 0.018899142000009306
},
"TrainerController.start_learning": {
"total": 440.46413696799993,
"count": 1,
"self": 0.37305347900871766,
"children": {
"TrainerController._reset_env": {
"total": 1.9607672769999454,
"count": 1,
"self": 1.9607672769999454
},
"TrainerController.advance": {
"total": 438.0325265629914,
"count": 18192,
"self": 0.38779788198723963,
"children": {
"env_step": {
"total": 310.8578785089911,
"count": 18192,
"self": 235.05389938701262,
"children": {
"SubprocessEnvManager._take_step": {
"total": 75.58495331899303,
"count": 18192,
"self": 1.318898601012279,
"children": {
"TorchPolicy.evaluate": {
"total": 74.26605471798075,
"count": 18192,
"self": 74.26605471798075
}
}
},
"workers": {
"total": 0.21902580298547036,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 438.96235547299716,
"count": 18192,
"is_parallel": true,
"self": 233.12389703897247,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002182607999998254,
"count": 1,
"is_parallel": true,
"self": 0.0006951860001436216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014874219998546323,
"count": 10,
"is_parallel": true,
"self": 0.0014874219998546323
}
}
},
"UnityEnvironment.step": {
"total": 0.0689939559999857,
"count": 1,
"is_parallel": true,
"self": 0.0005842089999532618,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000491914999997789,
"count": 1,
"is_parallel": true,
"self": 0.000491914999997789
},
"communicator.exchange": {
"total": 0.06488138800000343,
"count": 1,
"is_parallel": true,
"self": 0.06488138800000343
},
"steps_from_proto": {
"total": 0.0030364440000312243,
"count": 1,
"is_parallel": true,
"self": 0.0003796180001245375,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026568259999066868,
"count": 10,
"is_parallel": true,
"self": 0.0026568259999066868
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 205.8384584340247,
"count": 18191,
"is_parallel": true,
"self": 9.666482508044624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.449876918002246,
"count": 18191,
"is_parallel": true,
"self": 5.449876918002246
},
"communicator.exchange": {
"total": 158.00050574897887,
"count": 18191,
"is_parallel": true,
"self": 158.00050574897887
},
"steps_from_proto": {
"total": 32.72159325899895,
"count": 18191,
"is_parallel": true,
"self": 5.955281643951821,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.76631161504713,
"count": 181910,
"is_parallel": true,
"self": 26.76631161504713
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 126.78685017201303,
"count": 18192,
"self": 0.47733530800780954,
"children": {
"process_trajectory": {
"total": 28.12510463800527,
"count": 18192,
"self": 27.712681846005125,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4124227920001431,
"count": 4,
"self": 0.4124227920001431
}
}
},
"_update_policy": {
"total": 98.18441022599995,
"count": 90,
"self": 39.47068192198867,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.71372830401128,
"count": 4587,
"self": 58.71372830401128
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3489998309523799e-06,
"count": 1,
"self": 1.3489998309523799e-06
},
"TrainerController._save_models": {
"total": 0.09778830000004746,
"count": 1,
"self": 0.0013454170000386512,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0964428830000088,
"count": 1,
"self": 0.0964428830000088
}
}
}
}
}
}
}