gabriellipsa's picture
version one
cc2e90d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8119296431541443,
"min": 0.7892999053001404,
"max": 2.8694567680358887,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7716.5791015625,
"min": 7716.5791015625,
"max": 29291.4140625,
"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": 13.02244758605957,
"min": 0.45158877968788147,
"max": 13.13813304901123,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2539.377197265625,
"min": 87.60822296142578,
"max": 2654.570068359375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06611852218880884,
"min": 0.062128775847311635,
"max": 0.07523615745566192,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26447408875523537,
"min": 0.24851510338924654,
"max": 0.350884966529431,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19454350651187055,
"min": 0.10897724449123238,
"max": 0.28336263323823613,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7781740260474822,
"min": 0.4359089779649295,
"max": 1.4115332084543564,
"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": 25.704545454545453,
"min": 3.1363636363636362,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 138.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.1363636363636362,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 138.0,
"max": 1409.0,
"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": "1742554559",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742555011"
},
"total": 452.214404993,
"count": 1,
"self": 0.5925669170001129,
"children": {
"run_training.setup": {
"total": 0.029005044999962593,
"count": 1,
"self": 0.029005044999962593
},
"TrainerController.start_learning": {
"total": 451.59283303099994,
"count": 1,
"self": 0.5891013170018482,
"children": {
"TrainerController._reset_env": {
"total": 3.0027435840000294,
"count": 1,
"self": 3.0027435840000294
},
"TrainerController.advance": {
"total": 447.9276199059981,
"count": 18192,
"self": 0.6463139229959438,
"children": {
"env_step": {
"total": 326.0406903410009,
"count": 18192,
"self": 276.13925342400967,
"children": {
"SubprocessEnvManager._take_step": {
"total": 49.549911727000506,
"count": 18192,
"self": 1.620828343010544,
"children": {
"TorchPolicy.evaluate": {
"total": 47.92908338398996,
"count": 18192,
"self": 47.92908338398996
}
}
},
"workers": {
"total": 0.35152518999075255,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.655355876012,
"count": 18192,
"is_parallel": true,
"self": 212.2179688090049,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005217779000020073,
"count": 1,
"is_parallel": true,
"self": 0.004137319000108164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001080459999911909,
"count": 10,
"is_parallel": true,
"self": 0.001080459999911909
}
}
},
"UnityEnvironment.step": {
"total": 0.05030032299998766,
"count": 1,
"is_parallel": true,
"self": 0.0006712000000561602,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003832499999703032,
"count": 1,
"is_parallel": true,
"self": 0.0003832499999703032
},
"communicator.exchange": {
"total": 0.039882893999958924,
"count": 1,
"is_parallel": true,
"self": 0.039882893999958924
},
"steps_from_proto": {
"total": 0.00936297900000227,
"count": 1,
"is_parallel": true,
"self": 0.004556318999902942,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004806660000099328,
"count": 10,
"is_parallel": true,
"self": 0.004806660000099328
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.43738706700708,
"count": 18191,
"is_parallel": true,
"self": 11.371483275017397,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.523137882997105,
"count": 18191,
"is_parallel": true,
"self": 6.523137882997105
},
"communicator.exchange": {
"total": 187.68167947299247,
"count": 18191,
"is_parallel": true,
"self": 187.68167947299247
},
"steps_from_proto": {
"total": 31.861086436000107,
"count": 18191,
"is_parallel": true,
"self": 6.489183250004089,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.37190318599602,
"count": 181910,
"is_parallel": true,
"self": 25.37190318599602
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.24061564200122,
"count": 18192,
"self": 0.8446056739906567,
"children": {
"process_trajectory": {
"total": 26.006163987010666,
"count": 18192,
"self": 25.66547117501051,
"children": {
"RLTrainer._checkpoint": {
"total": 0.34069281200015666,
"count": 4,
"self": 0.34069281200015666
}
}
},
"_update_policy": {
"total": 94.3898459809999,
"count": 90,
"self": 35.18704222900192,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.202803751997976,
"count": 4587,
"self": 59.202803751997976
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.829999973779195e-06,
"count": 1,
"self": 1.829999973779195e-06
},
"TrainerController._save_models": {
"total": 0.07336639400000422,
"count": 1,
"self": 0.0013026299999410185,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0720637640000632,
"count": 1,
"self": 0.0720637640000632
}
}
}
}
}
}
}