mmichiels13's picture
First Push
8a58318 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.851479172706604,
"min": 0.851479172706604,
"max": 2.864454984664917,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8092.4580078125,
"min": 8092.4580078125,
"max": 29240.35546875,
"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": 12.984848022460938,
"min": 0.3729057013988495,
"max": 12.984848022460938,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2532.04541015625,
"min": 72.34370422363281,
"max": 2638.978515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07004682535754161,
"min": 0.0641758680389923,
"max": 0.07286961077959003,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28018730143016646,
"min": 0.2567034721559692,
"max": 0.36434805389795016,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2067087765271757,
"min": 0.10037071395017133,
"max": 0.2826615608498162,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8268351061087028,
"min": 0.4014828558006853,
"max": 1.3746135287425099,
"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": 25.113636363636363,
"min": 2.5,
"max": 25.6,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 110.0,
"max": 1408.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 2.5,
"max": 25.6,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 110.0,
"max": 1408.0,
"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": "1767327622",
"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": "1767328056"
},
"total": 434.2162658590005,
"count": 1,
"self": 0.7939591699996527,
"children": {
"run_training.setup": {
"total": 0.0307480650008074,
"count": 1,
"self": 0.0307480650008074
},
"TrainerController.start_learning": {
"total": 433.391558624,
"count": 1,
"self": 0.34209546115016565,
"children": {
"TrainerController._reset_env": {
"total": 4.654526079999414,
"count": 1,
"self": 4.654526079999414
},
"TrainerController.advance": {
"total": 428.2908890888484,
"count": 18192,
"self": 0.35386911177010916,
"children": {
"env_step": {
"total": 311.28590199518294,
"count": 18192,
"self": 243.58629871147605,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.47744267885537,
"count": 18192,
"self": 1.2701683758368745,
"children": {
"TorchPolicy.evaluate": {
"total": 66.2072743030185,
"count": 18192,
"self": 66.2072743030185
}
}
},
"workers": {
"total": 0.2221606048515241,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 431.50465233423347,
"count": 18192,
"is_parallel": true,
"self": 217.4016946551401,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006616911001401604,
"count": 1,
"is_parallel": true,
"self": 0.004371296001409064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00224561499999254,
"count": 10,
"is_parallel": true,
"self": 0.00224561499999254
}
}
},
"UnityEnvironment.step": {
"total": 0.06550541599972348,
"count": 1,
"is_parallel": true,
"self": 0.0005671100007020868,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004274119983165292,
"count": 1,
"is_parallel": true,
"self": 0.0004274119983165292
},
"communicator.exchange": {
"total": 0.061965611999767134,
"count": 1,
"is_parallel": true,
"self": 0.061965611999767134
},
"steps_from_proto": {
"total": 0.002545282000937732,
"count": 1,
"is_parallel": true,
"self": 0.00043637999988277443,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021089020010549575,
"count": 10,
"is_parallel": true,
"self": 0.0021089020010549575
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.10295767909338,
"count": 18191,
"is_parallel": true,
"self": 10.09885873107305,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.366857228033041,
"count": 18191,
"is_parallel": true,
"self": 5.366857228033041
},
"communicator.exchange": {
"total": 162.99293258202488,
"count": 18191,
"is_parallel": true,
"self": 162.99293258202488
},
"steps_from_proto": {
"total": 35.64430913796241,
"count": 18191,
"is_parallel": true,
"self": 6.5147935067652725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.129515631197137,
"count": 181910,
"is_parallel": true,
"self": 29.129515631197137
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.65111798189537,
"count": 18192,
"self": 0.44578799183364026,
"children": {
"process_trajectory": {
"total": 26.39081999605878,
"count": 18192,
"self": 25.852969621057127,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5378503750016534,
"count": 4,
"self": 0.5378503750016534
}
}
},
"_update_policy": {
"total": 89.81450999400295,
"count": 90,
"self": 36.462208824024856,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.35230116997809,
"count": 4587,
"self": 53.35230116997809
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2320015230216086e-06,
"count": 1,
"self": 1.2320015230216086e-06
},
"TrainerController._save_models": {
"total": 0.10404676200050744,
"count": 1,
"self": 0.0008299940000142669,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10321676800049318,
"count": 1,
"self": 0.10321676800049318
}
}
}
}
}
}
}