bird3314's picture
First Push
cdc90e1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.905120313167572,
"min": 0.905120313167572,
"max": 2.854132890701294,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8602.263671875,
"min": 8602.263671875,
"max": 29134.98828125,
"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": 13.147195816040039,
"min": 0.2383708506822586,
"max": 13.147195816040039,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2563.703125,
"min": 46.24394607543945,
"max": 2678.5400390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06961394335125007,
"min": 0.06479861523554313,
"max": 0.07585845142443134,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2784557734050003,
"min": 0.26596503525712145,
"max": 0.37929225712215675,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2072681217801337,
"min": 0.12907265410667249,
"max": 0.303845577730852,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8290724871205348,
"min": 0.5162906164266899,
"max": 1.51922788865426,
"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": 25.863636363636363,
"min": 3.6363636363636362,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1138.0,
"min": 160.0,
"max": 1420.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.863636363636363,
"min": 3.6363636363636362,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1138.0,
"min": 160.0,
"max": 1420.0,
"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": "1778407388",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1778407881"
},
"total": 493.1093735929999,
"count": 1,
"self": 0.9038848210000197,
"children": {
"run_training.setup": {
"total": 0.02723172599985446,
"count": 1,
"self": 0.02723172599985446
},
"TrainerController.start_learning": {
"total": 492.178257046,
"count": 1,
"self": 0.4212958149714723,
"children": {
"TrainerController._reset_env": {
"total": 3.518331900000021,
"count": 1,
"self": 3.518331900000021
},
"TrainerController.advance": {
"total": 488.10142376602835,
"count": 18192,
"self": 0.4366136400328742,
"children": {
"env_step": {
"total": 358.20984413698716,
"count": 18192,
"self": 279.25832133699987,
"children": {
"SubprocessEnvManager._take_step": {
"total": 78.69408990100328,
"count": 18192,
"self": 1.4005055710094894,
"children": {
"TorchPolicy.evaluate": {
"total": 77.29358432999379,
"count": 18192,
"self": 77.29358432999379
}
}
},
"workers": {
"total": 0.2574328989840069,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 489.98544624300393,
"count": 18192,
"is_parallel": true,
"self": 244.92779549800775,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005383975000086139,
"count": 1,
"is_parallel": true,
"self": 0.003993169000068519,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013908060000176192,
"count": 10,
"is_parallel": true,
"self": 0.0013908060000176192
}
}
},
"UnityEnvironment.step": {
"total": 0.03910324799994669,
"count": 1,
"is_parallel": true,
"self": 0.0006542989997342374,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005050210002082167,
"count": 1,
"is_parallel": true,
"self": 0.0005050210002082167
},
"communicator.exchange": {
"total": 0.03573339199988368,
"count": 1,
"is_parallel": true,
"self": 0.03573339199988368
},
"steps_from_proto": {
"total": 0.0022105360001205554,
"count": 1,
"is_parallel": true,
"self": 0.0004483820002860739,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017621539998344815,
"count": 10,
"is_parallel": true,
"self": 0.0017621539998344815
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.05765074499618,
"count": 18191,
"is_parallel": true,
"self": 11.154790912011094,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.05683733998535,
"count": 18191,
"is_parallel": true,
"self": 6.05683733998535
},
"communicator.exchange": {
"total": 187.42793755899743,
"count": 18191,
"is_parallel": true,
"self": 187.42793755899743
},
"steps_from_proto": {
"total": 40.41808493400231,
"count": 18191,
"is_parallel": true,
"self": 7.040909263978847,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.37717567002346,
"count": 181910,
"is_parallel": true,
"self": 33.37717567002346
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 129.45496598900831,
"count": 18192,
"self": 0.527922872003046,
"children": {
"process_trajectory": {
"total": 28.745497271003615,
"count": 18192,
"self": 28.25588681500335,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4896104560002641,
"count": 4,
"self": 0.4896104560002641
}
}
},
"_update_policy": {
"total": 100.18154584600165,
"count": 90,
"self": 40.710391484008596,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.47115436199306,
"count": 4587,
"self": 59.47115436199306
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6999999843392288e-06,
"count": 1,
"self": 1.6999999843392288e-06
},
"TrainerController._save_models": {
"total": 0.13720386500017412,
"count": 1,
"self": 0.0010112170000411425,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13619264800013298,
"count": 1,
"self": 0.13619264800013298
}
}
}
}
}
}
}