Fildu's picture
First Push
16643d2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9524787664413452,
"min": 0.9524787664413452,
"max": 2.8344082832336426,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9052.3583984375,
"min": 9052.3583984375,
"max": 28933.640625,
"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": 13.50263500213623,
"min": 0.4581652879714966,
"max": 13.570494651794434,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2633.013916015625,
"min": 88.88406372070312,
"max": 2768.380859375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07052752182156409,
"min": 0.06365462587831323,
"max": 0.07385758283111607,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28211008728625636,
"min": 0.26861162144337225,
"max": 0.3548577390760971,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1847459038171698,
"min": 0.15489606960156166,
"max": 0.292522631585598,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7389836152686792,
"min": 0.6195842784062466,
"max": 1.259341530063573,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000009e-06,
"min": 8.082097306000009e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2328389224000035e-05,
"min": 3.2328389224000035e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999998,
"min": 0.10269399999999998,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4107759999999999,
"min": 0.4107759999999999,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"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": 26.045454545454547,
"min": 4.454545454545454,
"max": 26.87272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1146.0,
"min": 196.0,
"max": 1478.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.045454545454547,
"min": 4.454545454545454,
"max": 26.87272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1146.0,
"min": 196.0,
"max": 1478.0,
"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": "1750802079",
"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": "1750802588"
},
"total": 508.55779521600016,
"count": 1,
"self": 0.4837437240003055,
"children": {
"run_training.setup": {
"total": 0.024020907999783958,
"count": 1,
"self": 0.024020907999783958
},
"TrainerController.start_learning": {
"total": 508.05003058400007,
"count": 1,
"self": 0.34411290000525696,
"children": {
"TrainerController._reset_env": {
"total": 3.3603872839998985,
"count": 1,
"self": 3.3603872839998985
},
"TrainerController.advance": {
"total": 504.24592283599486,
"count": 18192,
"self": 0.38533446501787694,
"children": {
"env_step": {
"total": 307.71629884301046,
"count": 18192,
"self": 236.7395219139321,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.76045543602231,
"count": 18192,
"self": 1.2579724140296094,
"children": {
"TorchPolicy.evaluate": {
"total": 69.5024830219927,
"count": 18192,
"self": 69.5024830219927
}
}
},
"workers": {
"total": 0.21632149305605708,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 506.63854552702924,
"count": 18192,
"is_parallel": true,
"self": 298.1648919080062,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005833455999891157,
"count": 1,
"is_parallel": true,
"self": 0.004430226998920261,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014032290009708959,
"count": 10,
"is_parallel": true,
"self": 0.0014032290009708959
}
}
},
"UnityEnvironment.step": {
"total": 0.03716694300010204,
"count": 1,
"is_parallel": true,
"self": 0.0006405759995686822,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000400405000164028,
"count": 1,
"is_parallel": true,
"self": 0.000400405000164028
},
"communicator.exchange": {
"total": 0.0342130349999934,
"count": 1,
"is_parallel": true,
"self": 0.0342130349999934
},
"steps_from_proto": {
"total": 0.0019129270003759302,
"count": 1,
"is_parallel": true,
"self": 0.0003586970010474033,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001554229999328527,
"count": 10,
"is_parallel": true,
"self": 0.001554229999328527
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.47365361902303,
"count": 18191,
"is_parallel": true,
"self": 10.112896175059177,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.622795911964204,
"count": 18191,
"is_parallel": true,
"self": 5.622795911964204
},
"communicator.exchange": {
"total": 160.79426873298962,
"count": 18191,
"is_parallel": true,
"self": 160.79426873298962
},
"steps_from_proto": {
"total": 31.943692799010023,
"count": 18191,
"is_parallel": true,
"self": 5.604125746887803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.33956705212222,
"count": 181910,
"is_parallel": true,
"self": 26.33956705212222
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 196.14428952796652,
"count": 18192,
"self": 0.42046861595235896,
"children": {
"process_trajectory": {
"total": 28.209107603010125,
"count": 18192,
"self": 27.671768528010034,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5373390750000908,
"count": 4,
"self": 0.5373390750000908
}
}
},
"_update_policy": {
"total": 167.51471330900404,
"count": 90,
"self": 66.73902432000204,
"children": {
"TorchPPOOptimizer.update": {
"total": 100.77568898900199,
"count": 7645,
"self": 100.77568898900199
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.509999472356867e-07,
"count": 1,
"self": 9.509999472356867e-07
},
"TrainerController._save_models": {
"total": 0.09960661300010543,
"count": 1,
"self": 0.0009638149999773304,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0986427980001281,
"count": 1,
"self": 0.0986427980001281
}
}
}
}
}
}
}