ray883's picture
First Push
49312d7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.851208508014679,
"min": 0.8413262367248535,
"max": 2.8359272480010986,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8089.8857421875,
"min": 8089.8857421875,
"max": 28949.14453125,
"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": 12.902095794677734,
"min": 0.36875107884407043,
"max": 12.902095794677734,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2515.90869140625,
"min": 71.53771209716797,
"max": 2602.517578125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0675103866193311,
"min": 0.06171914438178361,
"max": 0.07421055176154386,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2700415464773244,
"min": 0.24693542430174475,
"max": 0.36061360138495835,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20743080926145996,
"min": 0.11351285131954059,
"max": 0.28547376739043817,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8297232370458398,
"min": 0.45405140527816235,
"max": 1.4273688369521909,
"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": 25.295454545454547,
"min": 3.2954545454545454,
"max": 25.327272727272728,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 145.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.2954545454545454,
"max": 25.327272727272728,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 145.0,
"max": 1393.0,
"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": "1749008240",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749008703"
},
"total": 462.8448564549999,
"count": 1,
"self": 0.49654687699990063,
"children": {
"run_training.setup": {
"total": 0.025157921999948485,
"count": 1,
"self": 0.025157921999948485
},
"TrainerController.start_learning": {
"total": 462.32315165600005,
"count": 1,
"self": 0.42365262399061976,
"children": {
"TrainerController._reset_env": {
"total": 3.484786999999983,
"count": 1,
"self": 3.484786999999983
},
"TrainerController.advance": {
"total": 458.3293139550094,
"count": 18192,
"self": 0.45657400298648554,
"children": {
"env_step": {
"total": 325.91989722801304,
"count": 18192,
"self": 249.997421003024,
"children": {
"SubprocessEnvManager._take_step": {
"total": 75.68482586699076,
"count": 18192,
"self": 1.3823137949918873,
"children": {
"TorchPolicy.evaluate": {
"total": 74.30251207199888,
"count": 18192,
"self": 74.30251207199888
}
}
},
"workers": {
"total": 0.23765035799829093,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.8165667979923,
"count": 18192,
"is_parallel": true,
"self": 241.62149960199622,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004917496999951254,
"count": 1,
"is_parallel": true,
"self": 0.0034784939997507536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014390030002005005,
"count": 10,
"is_parallel": true,
"self": 0.0014390030002005005
}
}
},
"UnityEnvironment.step": {
"total": 0.05629736799994589,
"count": 1,
"is_parallel": true,
"self": 0.0006797770000730452,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041095899996435037,
"count": 1,
"is_parallel": true,
"self": 0.00041095899996435037
},
"communicator.exchange": {
"total": 0.04913287599993055,
"count": 1,
"is_parallel": true,
"self": 0.04913287599993055
},
"steps_from_proto": {
"total": 0.006073755999977948,
"count": 1,
"is_parallel": true,
"self": 0.004535378000127821,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015383779998501268,
"count": 10,
"is_parallel": true,
"self": 0.0015383779998501268
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.1950671959961,
"count": 18191,
"is_parallel": true,
"self": 10.23444841200751,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.639852019991281,
"count": 18191,
"is_parallel": true,
"self": 5.639852019991281
},
"communicator.exchange": {
"total": 170.01450863799823,
"count": 18191,
"is_parallel": true,
"self": 170.01450863799823
},
"steps_from_proto": {
"total": 33.30625812599908,
"count": 18191,
"is_parallel": true,
"self": 6.112842114969567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.193416011029512,
"count": 181910,
"is_parallel": true,
"self": 27.193416011029512
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 131.95284272400988,
"count": 18192,
"self": 0.5015770890039448,
"children": {
"process_trajectory": {
"total": 29.1661120410065,
"count": 18192,
"self": 28.697961144006626,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4681508969998731,
"count": 4,
"self": 0.4681508969998731
}
}
},
"_update_policy": {
"total": 102.28515359399944,
"count": 90,
"self": 41.98679748599932,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.29835610800012,
"count": 4587,
"self": 60.29835610800012
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.202000021294225e-06,
"count": 1,
"self": 1.202000021294225e-06
},
"TrainerController._save_models": {
"total": 0.08539687500001492,
"count": 1,
"self": 0.0009089160000712582,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08448795899994366,
"count": 1,
"self": 0.08448795899994366
}
}
}
}
}
}
}