Slavensky's picture
First Push
25d03e9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8131904006004333,
"min": 0.8131904006004333,
"max": 2.8306288719177246,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7728.5615234375,
"min": 7728.5615234375,
"max": 28895.05859375,
"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": 12.788293838500977,
"min": 0.5035483837127686,
"max": 12.788293838500977,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.71728515625,
"min": 97.68838500976562,
"max": 2600.3037109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06312184654776573,
"min": 0.06312184654776573,
"max": 0.07505035268173636,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2524873861910629,
"min": 0.2524873861910629,
"max": 0.3752517634086818,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1849638285736243,
"min": 0.13869059299616437,
"max": 0.29137082286909516,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7398553142944972,
"min": 0.5547623719846575,
"max": 1.4568541143454758,
"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": 25.113636363636363,
"min": 3.590909090909091,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 158.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 3.590909090909091,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 158.0,
"max": 1388.0,
"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": "1761509614",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/usr/local/envs/py310/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": "1761510047"
},
"total": 433.21374895400015,
"count": 1,
"self": 0.43920486600006825,
"children": {
"run_training.setup": {
"total": 0.03670538400001533,
"count": 1,
"self": 0.03670538400001533
},
"TrainerController.start_learning": {
"total": 432.73783870400007,
"count": 1,
"self": 0.34298997900327777,
"children": {
"TrainerController._reset_env": {
"total": 2.8491656009999815,
"count": 1,
"self": 2.8491656009999815
},
"TrainerController.advance": {
"total": 429.46167385199703,
"count": 18192,
"self": 0.36513463499693444,
"children": {
"env_step": {
"total": 311.1029650789884,
"count": 18192,
"self": 243.42630958298616,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.46740968200368,
"count": 18192,
"self": 1.2318899700077282,
"children": {
"TorchPolicy.evaluate": {
"total": 66.23551971199595,
"count": 18192,
"self": 66.23551971199595
}
}
},
"workers": {
"total": 0.2092458139985638,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.8891445889867,
"count": 18192,
"is_parallel": true,
"self": 217.14582461999385,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00481328199998643,
"count": 1,
"is_parallel": true,
"self": 0.003496194999911495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013170870000749346,
"count": 10,
"is_parallel": true,
"self": 0.0013170870000749346
}
}
},
"UnityEnvironment.step": {
"total": 0.037121086999945874,
"count": 1,
"is_parallel": true,
"self": 0.0006093050001254596,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042198699998152733,
"count": 1,
"is_parallel": true,
"self": 0.00042198699998152733
},
"communicator.exchange": {
"total": 0.03236601099990821,
"count": 1,
"is_parallel": true,
"self": 0.03236601099990821
},
"steps_from_proto": {
"total": 0.0037237839999306743,
"count": 1,
"is_parallel": true,
"self": 0.00036671599991677795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0033570680000138964,
"count": 10,
"is_parallel": true,
"self": 0.0033570680000138964
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 213.74331996899286,
"count": 18191,
"is_parallel": true,
"self": 9.97128402201622,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.364550226987831,
"count": 18191,
"is_parallel": true,
"self": 5.364550226987831
},
"communicator.exchange": {
"total": 162.92738268698645,
"count": 18191,
"is_parallel": true,
"self": 162.92738268698645
},
"steps_from_proto": {
"total": 35.480103033002365,
"count": 18191,
"is_parallel": true,
"self": 6.548850035999749,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.931252997002616,
"count": 181910,
"is_parallel": true,
"self": 28.931252997002616
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.9935741380117,
"count": 18192,
"self": 0.43765084800872955,
"children": {
"process_trajectory": {
"total": 25.793153852003,
"count": 18192,
"self": 25.41357575900281,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3795780930001911,
"count": 4,
"self": 0.3795780930001911
}
}
},
"_update_policy": {
"total": 91.76276943799996,
"count": 90,
"self": 38.19766013399885,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.56510930400111,
"count": 4587,
"self": 53.56510930400111
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1509998785186326e-06,
"count": 1,
"self": 1.1509998785186326e-06
},
"TrainerController._save_models": {
"total": 0.08400812099989707,
"count": 1,
"self": 0.0007733889997325605,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08323473200016451,
"count": 1,
"self": 0.08323473200016451
}
}
}
}
}
}
}