AE1999's picture
First Push
badba9c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.934474766254425,
"min": 0.934474766254425,
"max": 2.856671094894409,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8881.248046875,
"min": 8881.248046875,
"max": 29160.8984375,
"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": 13.663902282714844,
"min": 0.5015750527381897,
"max": 13.690448760986328,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2664.4609375,
"min": 97.3055648803711,
"max": 2792.8515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.05991699727390227,
"min": 0.05991699727390227,
"max": 0.07736749140752307,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.23966798909560907,
"min": 0.23966798909560907,
"max": 0.3645169942938795,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20482642692970293,
"min": 0.14139899285281915,
"max": 0.33085853095148127,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8193057077188117,
"min": 0.5655959714112766,
"max": 1.485425074895223,
"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": 3.6670600000000014e-05,
"min": 3.6670600000000014e-05,
"max": 0.0009732106000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00014668240000000006,
"min": 0.00014668240000000006,
"max": 0.004621028,
"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": 26.65909090909091,
"min": 3.590909090909091,
"max": 27.25,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1173.0,
"min": 158.0,
"max": 1493.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.65909090909091,
"min": 3.590909090909091,
"max": 27.25,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1173.0,
"min": 158.0,
"max": 1493.0,
"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": "1739819823",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /kaggle/input/snowballtarget2/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": "1739820240"
},
"total": 417.007247407,
"count": 1,
"self": 0.32142815000008795,
"children": {
"run_training.setup": {
"total": 0.021526232000042,
"count": 1,
"self": 0.021526232000042
},
"TrainerController.start_learning": {
"total": 416.6642930249999,
"count": 1,
"self": 0.30419893699922795,
"children": {
"TrainerController._reset_env": {
"total": 2.1394153649999907,
"count": 1,
"self": 2.1394153649999907
},
"TrainerController.advance": {
"total": 414.1017530960006,
"count": 18192,
"self": 0.3341372159925413,
"children": {
"env_step": {
"total": 280.6157318960006,
"count": 18192,
"self": 205.63386003200685,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.78193932999409,
"count": 18192,
"self": 1.1690141939930072,
"children": {
"TorchPolicy.evaluate": {
"total": 73.61292513600108,
"count": 18192,
"self": 73.61292513600108
}
}
},
"workers": {
"total": 0.1999325339996858,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 415.73351217300296,
"count": 18192,
"is_parallel": true,
"self": 234.51235293000184,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002393755999946734,
"count": 1,
"is_parallel": true,
"self": 0.0008149529999172955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015788030000294384,
"count": 10,
"is_parallel": true,
"self": 0.0015788030000294384
}
}
},
"UnityEnvironment.step": {
"total": 0.0385736089999682,
"count": 1,
"is_parallel": true,
"self": 0.0006753330000037749,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000446145999944747,
"count": 1,
"is_parallel": true,
"self": 0.000446145999944747
},
"communicator.exchange": {
"total": 0.035344700999985434,
"count": 1,
"is_parallel": true,
"self": 0.035344700999985434
},
"steps_from_proto": {
"total": 0.0021074290000342444,
"count": 1,
"is_parallel": true,
"self": 0.00038918299992474203,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017182460001095023,
"count": 10,
"is_parallel": true,
"self": 0.0017182460001095023
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 181.22115924300113,
"count": 18191,
"is_parallel": true,
"self": 7.558301619994154,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.078275990009047,
"count": 18191,
"is_parallel": true,
"self": 4.078275990009047
},
"communicator.exchange": {
"total": 144.11744067400673,
"count": 18191,
"is_parallel": true,
"self": 144.11744067400673
},
"steps_from_proto": {
"total": 25.467140958991195,
"count": 18191,
"is_parallel": true,
"self": 4.780782958015834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 20.68635800097536,
"count": 181910,
"is_parallel": true,
"self": 20.68635800097536
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 133.15188398400744,
"count": 18192,
"self": 0.3649334660119621,
"children": {
"process_trajectory": {
"total": 43.540624665995324,
"count": 18192,
"self": 43.01546571499523,
"children": {
"RLTrainer._checkpoint": {
"total": 0.525158951000094,
"count": 4,
"self": 0.525158951000094
}
}
},
"_update_policy": {
"total": 89.24632585200015,
"count": 90,
"self": 33.53912318000073,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.707202671999426,
"count": 4587,
"self": 55.707202671999426
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.860000318440143e-07,
"count": 1,
"self": 9.860000318440143e-07
},
"TrainerController._save_models": {
"total": 0.11892464100003508,
"count": 1,
"self": 0.0009081520000790988,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11801648899995598,
"count": 1,
"self": 0.11801648899995598
}
}
}
}
}
}
}