Juan Francisco Kurucz
First Push
bf20033
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0517128705978394,
"min": 1.0517128705978394,
"max": 2.8636863231658936,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10041.7548828125,
"min": 10041.7548828125,
"max": 29327.01171875,
"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": 12.76134967803955,
"min": 0.410555899143219,
"max": 12.76134967803955,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2488.463134765625,
"min": 79.64784240722656,
"max": 2559.533203125,
"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": 0.07192347138434164,
"min": 0.06072578658475358,
"max": 0.07359031800468288,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2876938855373666,
"min": 0.26443304558964814,
"max": 0.3600143445530158,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19802823071094122,
"min": 0.12675655536198369,
"max": 0.2725084220223567,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7921129228437649,
"min": 0.5070262214479347,
"max": 1.3102871734721988,
"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": 25.84090909090909,
"min": 3.772727272727273,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 166.0,
"max": 1366.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.772727272727273,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 166.0,
"max": 1366.0,
"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": "1684602309",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1684602761"
},
"total": 451.90770126599995,
"count": 1,
"self": 0.43484144299998206,
"children": {
"run_training.setup": {
"total": 0.039678035999997974,
"count": 1,
"self": 0.039678035999997974
},
"TrainerController.start_learning": {
"total": 451.43318178699997,
"count": 1,
"self": 0.5257987860077833,
"children": {
"TrainerController._reset_env": {
"total": 4.446249851000005,
"count": 1,
"self": 4.446249851000005
},
"TrainerController.advance": {
"total": 446.33056449599223,
"count": 18201,
"self": 0.2603152889876128,
"children": {
"env_step": {
"total": 446.0702492070046,
"count": 18201,
"self": 324.5415170380063,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.27984592700125,
"count": 18201,
"self": 1.6928454950079868,
"children": {
"TorchPolicy.evaluate": {
"total": 119.58700043199326,
"count": 18201,
"self": 119.58700043199326
}
}
},
"workers": {
"total": 0.2488862419970701,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.90768030099247,
"count": 18201,
"is_parallel": true,
"self": 211.75920040298826,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004301349999991544,
"count": 1,
"is_parallel": true,
"self": 0.0027963629999021578,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015049870000893861,
"count": 10,
"is_parallel": true,
"self": 0.0015049870000893861
}
}
},
"UnityEnvironment.step": {
"total": 0.059558570000035616,
"count": 1,
"is_parallel": true,
"self": 0.0005612570001289896,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040156899996190987,
"count": 1,
"is_parallel": true,
"self": 0.00040156899996190987
},
"communicator.exchange": {
"total": 0.05666564899996729,
"count": 1,
"is_parallel": true,
"self": 0.05666564899996729
},
"steps_from_proto": {
"total": 0.0019300949999774275,
"count": 1,
"is_parallel": true,
"self": 0.00036318799999435214,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015669069999830754,
"count": 10,
"is_parallel": true,
"self": 0.0015669069999830754
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.1484798980042,
"count": 18200,
"is_parallel": true,
"self": 9.247842503998356,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.035159997004428,
"count": 18200,
"is_parallel": true,
"self": 5.035159997004428
},
"communicator.exchange": {
"total": 191.79838072600046,
"count": 18200,
"is_parallel": true,
"self": 191.79838072600046
},
"steps_from_proto": {
"total": 32.06709667100097,
"count": 18200,
"is_parallel": true,
"self": 6.114773118986591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.952323552014377,
"count": 182000,
"is_parallel": true,
"self": 25.952323552014377
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010850299997855473,
"count": 1,
"self": 0.00010850299997855473,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 442.96203042900135,
"count": 423770,
"is_parallel": true,
"self": 9.444256060000612,
"children": {
"process_trajectory": {
"total": 241.70016454100085,
"count": 423770,
"is_parallel": true,
"self": 240.39247487300088,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3076896679999663,
"count": 4,
"is_parallel": true,
"self": 1.3076896679999663
}
}
},
"_update_policy": {
"total": 191.8176098279999,
"count": 90,
"is_parallel": true,
"self": 70.67631047200274,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.14129935599715,
"count": 4587,
"is_parallel": true,
"self": 121.14129935599715
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13046015099996566,
"count": 1,
"self": 0.0009024260000387585,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1295577249999269,
"count": 1,
"self": 0.1295577249999269
}
}
}
}
}
}
}