niratpatel's picture
First Push
2ce1240 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6976195573806763,
"min": 0.6891975998878479,
"max": 2.8369338512420654,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6630.17626953125,
"min": 6630.17626953125,
"max": 28959.421875,
"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": 12.628561019897461,
"min": 0.4386715590953827,
"max": 12.628561019897461,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2462.5693359375,
"min": 85.10227966308594,
"max": 2573.636962890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06834074966187187,
"min": 0.06267426941614009,
"max": 0.07673879417064859,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2733629986474875,
"min": 0.25069707766456034,
"max": 0.3709667529431445,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19501759327363732,
"min": 0.12594808855404457,
"max": 0.2725881014384476,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7800703730945493,
"min": 0.5037923542161783,
"max": 1.3629405071922378,
"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": 25.068181818181817,
"min": 3.6136363636363638,
"max": 25.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1103.0,
"min": 159.0,
"max": 1373.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.068181818181817,
"min": 3.6136363636363638,
"max": 25.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1103.0,
"min": 159.0,
"max": 1373.0,
"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": "1745925885",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745926303"
},
"total": 418.223557101,
"count": 1,
"self": 0.5955863300000601,
"children": {
"run_training.setup": {
"total": 0.023443099000019174,
"count": 1,
"self": 0.023443099000019174
},
"TrainerController.start_learning": {
"total": 417.6045276719999,
"count": 1,
"self": 0.33297035500493166,
"children": {
"TrainerController._reset_env": {
"total": 3.5349751350000815,
"count": 1,
"self": 3.5349751350000815
},
"TrainerController.advance": {
"total": 413.604672811995,
"count": 18192,
"self": 0.3645160969936114,
"children": {
"env_step": {
"total": 292.903445473004,
"count": 18192,
"self": 223.32049448400892,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.3900892159927,
"count": 18192,
"self": 1.2274092829911751,
"children": {
"TorchPolicy.evaluate": {
"total": 68.16267993300153,
"count": 18192,
"self": 68.16267993300153
}
}
},
"workers": {
"total": 0.1928617730023916,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 416.10831611400477,
"count": 18192,
"is_parallel": true,
"self": 219.7711192070036,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0058266459999458675,
"count": 1,
"is_parallel": true,
"self": 0.004383408999956373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014432369999894945,
"count": 10,
"is_parallel": true,
"self": 0.0014432369999894945
}
}
},
"UnityEnvironment.step": {
"total": 0.03450124800008325,
"count": 1,
"is_parallel": true,
"self": 0.0006267750001143213,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004015569999182844,
"count": 1,
"is_parallel": true,
"self": 0.0004015569999182844
},
"communicator.exchange": {
"total": 0.031574228000067706,
"count": 1,
"is_parallel": true,
"self": 0.031574228000067706
},
"steps_from_proto": {
"total": 0.0018986879999829398,
"count": 1,
"is_parallel": true,
"self": 0.00036405800005923084,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001534629999923709,
"count": 10,
"is_parallel": true,
"self": 0.001534629999923709
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 196.33719690700116,
"count": 18191,
"is_parallel": true,
"self": 9.643746271007672,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3327958820033246,
"count": 18191,
"is_parallel": true,
"self": 5.3327958820033246
},
"communicator.exchange": {
"total": 150.90792761699083,
"count": 18191,
"is_parallel": true,
"self": 150.90792761699083
},
"steps_from_proto": {
"total": 30.45272713699933,
"count": 18191,
"is_parallel": true,
"self": 5.387008932036679,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.06571820496265,
"count": 181910,
"is_parallel": true,
"self": 25.06571820496265
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.33671124199736,
"count": 18192,
"self": 0.420700331000603,
"children": {
"process_trajectory": {
"total": 26.08729680699662,
"count": 18192,
"self": 25.61424824499659,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47304856200003087,
"count": 4,
"self": 0.47304856200003087
}
}
},
"_update_policy": {
"total": 93.82871410400014,
"count": 90,
"self": 37.63562336800737,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.19309073599277,
"count": 4587,
"self": 56.19309073599277
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.247000000148546e-06,
"count": 1,
"self": 1.247000000148546e-06
},
"TrainerController._save_models": {
"total": 0.13190812299990284,
"count": 1,
"self": 0.0010134999999991123,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13089462299990373,
"count": 1,
"self": 0.13089462299990373
}
}
}
}
}
}
}