adrian-nf's picture
First Push
5b6afb8 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8483105301856995,
"min": 0.8422937989234924,
"max": 2.866182327270508,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8127.6630859375,
"min": 8127.6630859375,
"max": 29384.1015625,
"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": 12.8423490524292,
"min": 0.33363860845565796,
"max": 12.8423490524292,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.258056640625,
"min": 64.72589111328125,
"max": 2604.4462890625,
"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.Losses.PolicyLoss.mean": {
"value": 0.06816318675658954,
"min": 0.06019814865773215,
"max": 0.07274020839820378,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27265274702635817,
"min": 0.2407925946309286,
"max": 0.3637010419910189,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17061980550780015,
"min": 0.14103648608650865,
"max": 0.2884284089008967,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6824792220312006,
"min": 0.5641459443460346,
"max": 1.4421420445044837,
"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.CumulativeReward.mean": {
"value": 25.431818181818183,
"min": 4.113636363636363,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 181.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.431818181818183,
"min": 4.113636363636363,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 181.0,
"max": 1395.0,
"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": "1734079835",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734080446"
},
"total": 610.869602047,
"count": 1,
"self": 0.6305780809998396,
"children": {
"run_training.setup": {
"total": 0.10440816799996355,
"count": 1,
"self": 0.10440816799996355
},
"TrainerController.start_learning": {
"total": 610.1346157980001,
"count": 1,
"self": 0.9281251499820655,
"children": {
"TrainerController._reset_env": {
"total": 8.44147629300005,
"count": 1,
"self": 8.44147629300005
},
"TrainerController.advance": {
"total": 600.676744534018,
"count": 18204,
"self": 0.4315705270317949,
"children": {
"env_step": {
"total": 600.2451740069862,
"count": 18204,
"self": 461.47754567796153,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.34300250202762,
"count": 18204,
"self": 2.588295111017942,
"children": {
"TorchPolicy.evaluate": {
"total": 135.75470739100967,
"count": 18204,
"self": 135.75470739100967
}
}
},
"workers": {
"total": 0.424625826997044,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 608.1367770199884,
"count": 18204,
"is_parallel": true,
"self": 295.37367542200286,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00415281400000822,
"count": 1,
"is_parallel": true,
"self": 0.001450186999932157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027026270000760633,
"count": 10,
"is_parallel": true,
"self": 0.0027026270000760633
}
}
},
"UnityEnvironment.step": {
"total": 0.0757713270000977,
"count": 1,
"is_parallel": true,
"self": 0.0009502430001475659,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004893889999948442,
"count": 1,
"is_parallel": true,
"self": 0.0004893889999948442
},
"communicator.exchange": {
"total": 0.07167667600003824,
"count": 1,
"is_parallel": true,
"self": 0.07167667600003824
},
"steps_from_proto": {
"total": 0.002655018999917047,
"count": 1,
"is_parallel": true,
"self": 0.0005118469998706132,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002143172000046434,
"count": 10,
"is_parallel": true,
"self": 0.002143172000046434
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 312.7631015979855,
"count": 18203,
"is_parallel": true,
"self": 15.092256199972326,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.689071899001874,
"count": 18203,
"is_parallel": true,
"self": 7.689071899001874
},
"communicator.exchange": {
"total": 244.869329607003,
"count": 18203,
"is_parallel": true,
"self": 244.869329607003
},
"steps_from_proto": {
"total": 45.11244389200829,
"count": 18203,
"is_parallel": true,
"self": 8.843552728015538,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.26889116399275,
"count": 182030,
"is_parallel": true,
"self": 36.26889116399275
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0007154319998790015,
"count": 1,
"self": 0.0007154319998790015,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 593.6995935029564,
"count": 774443,
"is_parallel": true,
"self": 18.791739186980067,
"children": {
"process_trajectory": {
"total": 320.7791160619762,
"count": 774443,
"is_parallel": true,
"self": 320.0407030769761,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7384129850000818,
"count": 4,
"is_parallel": true,
"self": 0.7384129850000818
}
}
},
"_update_policy": {
"total": 254.12873825400015,
"count": 90,
"is_parallel": true,
"self": 71.36632322699711,
"children": {
"TorchPPOOptimizer.update": {
"total": 182.76241502700304,
"count": 4587,
"is_parallel": true,
"self": 182.76241502700304
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08755438900016088,
"count": 1,
"self": 0.0013076420002562372,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08624674699990464,
"count": 1,
"self": 0.08624674699990464
}
}
}
}
}
}
}