shamekhjr's picture
First submission
e6ef641 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8802551627159119,
"min": 0.8717166185379028,
"max": 2.866849184036255,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8433.724609375,
"min": 8433.724609375,
"max": 29454.0078125,
"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": 13.111763954162598,
"min": 0.4318452477455139,
"max": 13.111763954162598,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2556.7939453125,
"min": 83.7779769897461,
"max": 2657.3935546875,
"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.Losses.PolicyLoss.mean": {
"value": 0.072567653333096,
"min": 0.0641327797462616,
"max": 0.07538293421866375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.290270613332384,
"min": 0.26896792074765863,
"max": 0.3686554981334969,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20104603418240358,
"min": 0.1262656863979703,
"max": 0.28903918079301427,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8041841367296143,
"min": 0.5050627455918812,
"max": 1.4451959039650712,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291906002698,
"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": 0.19730199999999998,
"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": 0.004865369800000001,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.477272727272727,
"min": 3.4545454545454546,
"max": 26.054545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 152.0,
"max": 1433.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 3.4545454545454546,
"max": 26.054545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 152.0,
"max": 1433.0,
"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": "1710345207",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/home/shamekhjr/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710346033"
},
"total": 826.3827315380001,
"count": 1,
"self": 1.3786129540001184,
"children": {
"run_training.setup": {
"total": 0.033264983999970354,
"count": 1,
"self": 0.033264983999970354
},
"TrainerController.start_learning": {
"total": 824.9708536,
"count": 1,
"self": 0.7364749699863751,
"children": {
"TrainerController._reset_env": {
"total": 13.105681272000083,
"count": 1,
"self": 13.105681272000083
},
"TrainerController.advance": {
"total": 810.9949023270135,
"count": 18202,
"self": 0.3627555760174346,
"children": {
"env_step": {
"total": 810.6321467509961,
"count": 18202,
"self": 514.6765176979993,
"children": {
"SubprocessEnvManager._take_step": {
"total": 295.5864142859955,
"count": 18202,
"self": 2.194378029981408,
"children": {
"TorchPolicy.evaluate": {
"total": 293.3920362560141,
"count": 18202,
"self": 293.3920362560141
}
}
},
"workers": {
"total": 0.3692147670012673,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 823.6267123310085,
"count": 18202,
"is_parallel": true,
"self": 424.8208703630098,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026050240001040947,
"count": 1,
"is_parallel": true,
"self": 0.0008288790004371549,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017761449996669398,
"count": 10,
"is_parallel": true,
"self": 0.0017761449996669398
}
}
},
"UnityEnvironment.step": {
"total": 0.046630824999965625,
"count": 1,
"is_parallel": true,
"self": 0.0004027610000321147,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0009509940000498318,
"count": 1,
"is_parallel": true,
"self": 0.0009509940000498318
},
"communicator.exchange": {
"total": 0.04350625699999,
"count": 1,
"is_parallel": true,
"self": 0.04350625699999
},
"steps_from_proto": {
"total": 0.0017708129998936784,
"count": 1,
"is_parallel": true,
"self": 0.0004800309991424001,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012907820007512782,
"count": 10,
"is_parallel": true,
"self": 0.0012907820007512782
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 398.80584196799873,
"count": 18201,
"is_parallel": true,
"self": 8.718288963018495,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3497231840019595,
"count": 18201,
"is_parallel": true,
"self": 5.3497231840019595
},
"communicator.exchange": {
"total": 357.0769473729822,
"count": 18201,
"is_parallel": true,
"self": 357.0769473729822
},
"steps_from_proto": {
"total": 27.660882447996073,
"count": 18201,
"is_parallel": true,
"self": 6.102169927996783,
"children": {
"_process_rank_one_or_two_observation": {
"total": 21.55871251999929,
"count": 182010,
"is_parallel": true,
"self": 21.55871251999929
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001424619999852439,
"count": 1,
"self": 0.0001424619999852439,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 804.9609080950513,
"count": 558951,
"is_parallel": true,
"self": 17.18461035404016,
"children": {
"process_trajectory": {
"total": 455.5821186620119,
"count": 558951,
"is_parallel": true,
"self": 454.6755135120118,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9066051500001322,
"count": 4,
"is_parallel": true,
"self": 0.9066051500001322
}
}
},
"_update_policy": {
"total": 332.19417907899924,
"count": 90,
"is_parallel": true,
"self": 40.189251648007485,
"children": {
"TorchPPOOptimizer.update": {
"total": 292.00492743099176,
"count": 4584,
"is_parallel": true,
"self": 292.00492743099176
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13365256900010536,
"count": 1,
"self": 0.0009394870000960509,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1327130820000093,
"count": 1,
"self": 0.1327130820000093
}
}
}
}
}
}
}