peggia's picture
First Push
15f385e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9407752156257629,
"min": 0.9407752156257629,
"max": 2.840545177459717,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8941.1279296875,
"min": 8941.1279296875,
"max": 28996.28515625,
"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": 12.81481647491455,
"min": 0.27760323882102966,
"max": 12.81481647491455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2498.88916015625,
"min": 53.85502624511719,
"max": 2603.13916015625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06896480700935867,
"min": 0.062088016039399695,
"max": 0.07545145359736304,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2758592280374347,
"min": 0.25401867675713685,
"max": 0.36391613475565215,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1736278069735158,
"min": 0.1145566309249832,
"max": 0.29078230889988876,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6945112278940632,
"min": 0.4582265236999328,
"max": 1.385697369482003,
"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": 25.681818181818183,
"min": 3.227272727272727,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 142.0,
"max": 1382.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 3.227272727272727,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 142.0,
"max": 1382.0,
"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": "1732799964",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn --force ./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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732800405"
},
"total": 440.44543656299993,
"count": 1,
"self": 0.425024318999931,
"children": {
"run_training.setup": {
"total": 0.06697687199994107,
"count": 1,
"self": 0.06697687199994107
},
"TrainerController.start_learning": {
"total": 439.95343537200006,
"count": 1,
"self": 0.3563548629699653,
"children": {
"TrainerController._reset_env": {
"total": 1.9738424870001836,
"count": 1,
"self": 1.9738424870001836
},
"TrainerController.advance": {
"total": 437.53929946902963,
"count": 18192,
"self": 0.3860574390378133,
"children": {
"env_step": {
"total": 309.40915743298046,
"count": 18192,
"self": 235.9623499979948,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.22497187602448,
"count": 18192,
"self": 1.329155159030961,
"children": {
"TorchPolicy.evaluate": {
"total": 71.89581671699352,
"count": 18192,
"self": 71.89581671699352
}
}
},
"workers": {
"total": 0.22183555896117468,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 438.51419277900413,
"count": 18192,
"is_parallel": true,
"self": 232.05980318795991,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0028261579996069486,
"count": 1,
"is_parallel": true,
"self": 0.0007681249985580507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002058033001048898,
"count": 10,
"is_parallel": true,
"self": 0.002058033001048898
}
}
},
"UnityEnvironment.step": {
"total": 0.034960006000346766,
"count": 1,
"is_parallel": true,
"self": 0.000641292000636895,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004284839997126255,
"count": 1,
"is_parallel": true,
"self": 0.0004284839997126255
},
"communicator.exchange": {
"total": 0.03183833799994318,
"count": 1,
"is_parallel": true,
"self": 0.03183833799994318
},
"steps_from_proto": {
"total": 0.0020518920000540675,
"count": 1,
"is_parallel": true,
"self": 0.00037018000011812546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001681711999935942,
"count": 10,
"is_parallel": true,
"self": 0.001681711999935942
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.45438959104422,
"count": 18191,
"is_parallel": true,
"self": 10.126523152049685,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.637455246048376,
"count": 18191,
"is_parallel": true,
"self": 5.637455246048376
},
"communicator.exchange": {
"total": 157.26438468000106,
"count": 18191,
"is_parallel": true,
"self": 157.26438468000106
},
"steps_from_proto": {
"total": 33.4260265129451,
"count": 18191,
"is_parallel": true,
"self": 6.048490809899704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.377535703045396,
"count": 181910,
"is_parallel": true,
"self": 27.377535703045396
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.74408459701135,
"count": 18192,
"self": 0.45063778299982005,
"children": {
"process_trajectory": {
"total": 28.90892581901153,
"count": 18192,
"self": 28.52738665701054,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3815391620009905,
"count": 4,
"self": 0.3815391620009905
}
}
},
"_update_policy": {
"total": 98.384520995,
"count": 90,
"self": 40.9112437189965,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.4732772760035,
"count": 4587,
"self": 57.4732772760035
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.644999883865239e-06,
"count": 1,
"self": 1.644999883865239e-06
},
"TrainerController._save_models": {
"total": 0.08393690800039622,
"count": 1,
"self": 0.0011513450003803882,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08278556300001583,
"count": 1,
"self": 0.08278556300001583
}
}
}
}
}
}
}