Sil3ntt's picture
First Push
3b8809c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8172892332077026,
"min": 0.8172892332077026,
"max": 2.827256441116333,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7767.5166015625,
"min": 7767.5166015625,
"max": 28860.6328125,
"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": 13.028785705566406,
"min": 0.5488582253456116,
"max": 13.028785705566406,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2540.61328125,
"min": 106.4784927368164,
"max": 2634.79931640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.071899542463892,
"min": 0.06360972276363777,
"max": 0.07880927417450129,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.287598169855568,
"min": 0.2568225615886702,
"max": 0.3689082212730165,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1914949707832991,
"min": 0.14886888323406525,
"max": 0.29700095069174676,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7659798831331964,
"min": 0.595475532936261,
"max": 1.4850047534587338,
"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": 25.931818181818183,
"min": 3.977272727272727,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 175.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.977272727272727,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 175.0,
"max": 1406.0,
"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": "1740489535",
"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": "1740489980"
},
"total": 445.174770845,
"count": 1,
"self": 0.4835027749998062,
"children": {
"run_training.setup": {
"total": 0.023512444000061805,
"count": 1,
"self": 0.023512444000061805
},
"TrainerController.start_learning": {
"total": 444.66775562600014,
"count": 1,
"self": 0.3917147050078711,
"children": {
"TrainerController._reset_env": {
"total": 3.2346184630000607,
"count": 1,
"self": 3.2346184630000607
},
"TrainerController.advance": {
"total": 440.9506579219924,
"count": 18192,
"self": 0.40702961101487745,
"children": {
"env_step": {
"total": 312.9244022469736,
"count": 18192,
"self": 238.76811977499506,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.9178586279952,
"count": 18192,
"self": 1.3134160520100977,
"children": {
"TorchPolicy.evaluate": {
"total": 72.6044425759851,
"count": 18192,
"self": 72.6044425759851
}
}
},
"workers": {
"total": 0.23842384398335525,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.0728496570082,
"count": 18192,
"is_parallel": true,
"self": 233.92673175700747,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0061335289999533416,
"count": 1,
"is_parallel": true,
"self": 0.00437554800032558,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017579809996277618,
"count": 10,
"is_parallel": true,
"self": 0.0017579809996277618
}
}
},
"UnityEnvironment.step": {
"total": 0.03789026200001899,
"count": 1,
"is_parallel": true,
"self": 0.0006779450002341036,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038857000004099973,
"count": 1,
"is_parallel": true,
"self": 0.00038857000004099973
},
"communicator.exchange": {
"total": 0.034682702999816684,
"count": 1,
"is_parallel": true,
"self": 0.034682702999816684
},
"steps_from_proto": {
"total": 0.0021410439999272057,
"count": 1,
"is_parallel": true,
"self": 0.00040899699956753466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001732047000359671,
"count": 10,
"is_parallel": true,
"self": 0.001732047000359671
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.14611790000072,
"count": 18191,
"is_parallel": true,
"self": 10.019052292994502,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.432845711995469,
"count": 18191,
"is_parallel": true,
"self": 5.432845711995469
},
"communicator.exchange": {
"total": 161.9157017850098,
"count": 18191,
"is_parallel": true,
"self": 161.9157017850098
},
"steps_from_proto": {
"total": 31.77851811000096,
"count": 18191,
"is_parallel": true,
"self": 5.677760320910693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.100757789090267,
"count": 181910,
"is_parallel": true,
"self": 26.100757789090267
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.6192260640039,
"count": 18192,
"self": 0.4837829120058359,
"children": {
"process_trajectory": {
"total": 27.408636582997588,
"count": 18192,
"self": 26.81775219399742,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5908843890001663,
"count": 4,
"self": 0.5908843890001663
}
}
},
"_update_policy": {
"total": 99.72680656900047,
"count": 90,
"self": 40.07380357700981,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.65300299199066,
"count": 4587,
"self": 59.65300299199066
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.589998626324814e-07,
"count": 1,
"self": 9.589998626324814e-07
},
"TrainerController._save_models": {
"total": 0.09076357699996151,
"count": 1,
"self": 0.0008780389998719329,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08988553800008958,
"count": 1,
"self": 0.08988553800008958
}
}
}
}
}
}
}