karthiklnagar16's picture
First Push
35dbb50 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9217273592948914,
"min": 0.9096651077270508,
"max": 2.839789867401123,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8760.0966796875,
"min": 8760.0966796875,
"max": 28988.576171875,
"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": 12.838403701782227,
"min": 0.3994563817977905,
"max": 12.838403701782227,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2503.48876953125,
"min": 77.49453735351562,
"max": 2604.87890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07036380253432035,
"min": 0.06377927244152398,
"max": 0.07511707091893471,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2814552101372814,
"min": 0.25511708976609593,
"max": 0.3576763875031497,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19993567612825655,
"min": 0.14155824171087028,
"max": 0.27191088019925,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7997427045130262,
"min": 0.5662329668434811,
"max": 1.3372567766437342,
"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": 3.6363636363636362,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 160.0,
"max": 1380.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.6363636363636362,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 160.0,
"max": 1380.0,
"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": "1773977543",
"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=SnowballTarget2 --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": "1773978020"
},
"total": 477.43827885099995,
"count": 1,
"self": 0.47614156799977536,
"children": {
"run_training.setup": {
"total": 0.025964512000200557,
"count": 1,
"self": 0.025964512000200557
},
"TrainerController.start_learning": {
"total": 476.936172771,
"count": 1,
"self": 0.4001751139855969,
"children": {
"TrainerController._reset_env": {
"total": 2.881020863999993,
"count": 1,
"self": 2.881020863999993
},
"TrainerController.advance": {
"total": 473.5647036710143,
"count": 18192,
"self": 0.4015871980279826,
"children": {
"env_step": {
"total": 345.73283015599327,
"count": 18192,
"self": 268.8577896989991,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.63479448899511,
"count": 18192,
"self": 1.360999265984674,
"children": {
"TorchPolicy.evaluate": {
"total": 75.27379522301044,
"count": 18192,
"self": 75.27379522301044
}
}
},
"workers": {
"total": 0.2402459679990443,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.91758619000734,
"count": 18192,
"is_parallel": true,
"self": 238.7626637950341,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004908880999892062,
"count": 1,
"is_parallel": true,
"self": 0.0033959429995320534,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001512938000360009,
"count": 10,
"is_parallel": true,
"self": 0.001512938000360009
}
}
},
"UnityEnvironment.step": {
"total": 0.07381348300009449,
"count": 1,
"is_parallel": true,
"self": 0.0006554090002737212,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000414137000007031,
"count": 1,
"is_parallel": true,
"self": 0.000414137000007031
},
"communicator.exchange": {
"total": 0.06751698299990494,
"count": 1,
"is_parallel": true,
"self": 0.06751698299990494
},
"steps_from_proto": {
"total": 0.005226953999908801,
"count": 1,
"is_parallel": true,
"self": 0.00039738099962960405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004829573000279197,
"count": 10,
"is_parallel": true,
"self": 0.004829573000279197
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.15492239497325,
"count": 18191,
"is_parallel": true,
"self": 10.753166447977947,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.855196432999037,
"count": 18191,
"is_parallel": true,
"self": 5.855196432999037
},
"communicator.exchange": {
"total": 179.5180993729998,
"count": 18191,
"is_parallel": true,
"self": 179.5180993729998
},
"steps_from_proto": {
"total": 40.02846014099646,
"count": 18191,
"is_parallel": true,
"self": 7.187892587057604,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.840567553938854,
"count": 181910,
"is_parallel": true,
"self": 32.840567553938854
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.43028631699303,
"count": 18192,
"self": 0.4943129940174913,
"children": {
"process_trajectory": {
"total": 28.475411310975005,
"count": 18192,
"self": 28.02329550297509,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4521158079999168,
"count": 4,
"self": 0.4521158079999168
}
}
},
"_update_policy": {
"total": 98.46056201200054,
"count": 90,
"self": 40.448208610001075,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.01235340199946,
"count": 4587,
"self": 58.01235340199946
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.590000900061568e-07,
"count": 1,
"self": 9.590000900061568e-07
},
"TrainerController._save_models": {
"total": 0.09027216300000873,
"count": 1,
"self": 0.0007742699999653269,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0894978930000434,
"count": 1,
"self": 0.0894978930000434
}
}
}
}
}
}
}