PR0G3T's picture
First Push
c8c9b4f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7685645222663879,
"min": 0.7685645222663879,
"max": 2.859574556350708,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7304.43701171875,
"min": 7304.43701171875,
"max": 29190.537109375,
"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": 12.900443077087402,
"min": 0.3348061740398407,
"max": 12.943016052246094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2515.58642578125,
"min": 64.95240020751953,
"max": 2640.375244140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06821936367658267,
"min": 0.06277587872298718,
"max": 0.07474097232753754,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2728774547063307,
"min": 0.25440856803199463,
"max": 0.36617762607170773,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22921156854021785,
"min": 0.12069639650301314,
"max": 0.29345249917869476,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9168462741608714,
"min": 0.48278558601205257,
"max": 1.45961154033156,
"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": 25.181818181818183,
"min": 3.1363636363636362,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1108.0,
"min": 138.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.181818181818183,
"min": 3.1363636363636362,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1108.0,
"min": 138.0,
"max": 1407.0,
"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": "1746004994",
"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": "1746005549"
},
"total": 554.8766706690001,
"count": 1,
"self": 1.0066598400001112,
"children": {
"run_training.setup": {
"total": 0.028866382999979123,
"count": 1,
"self": 0.028866382999979123
},
"TrainerController.start_learning": {
"total": 553.8411444459999,
"count": 1,
"self": 0.5994276250009989,
"children": {
"TrainerController._reset_env": {
"total": 3.4994222660000105,
"count": 1,
"self": 3.4994222660000105
},
"TrainerController.advance": {
"total": 549.629882954999,
"count": 18192,
"self": 0.6117295559888589,
"children": {
"env_step": {
"total": 384.3924875799992,
"count": 18192,
"self": 326.30628075499095,
"children": {
"SubprocessEnvManager._take_step": {
"total": 57.725447252001686,
"count": 18192,
"self": 1.9502847780049706,
"children": {
"TorchPolicy.evaluate": {
"total": 55.775162473996716,
"count": 18192,
"self": 55.775162473996716
}
}
},
"workers": {
"total": 0.36075957300658956,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 551.8334045589994,
"count": 18192,
"is_parallel": true,
"self": 269.15553920399714,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006739623999976629,
"count": 1,
"is_parallel": true,
"self": 0.0049978679999753695,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00174175600000126,
"count": 10,
"is_parallel": true,
"self": 0.00174175600000126
}
}
},
"UnityEnvironment.step": {
"total": 0.04946188399998164,
"count": 1,
"is_parallel": true,
"self": 0.0007634479999865107,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005196740000315003,
"count": 1,
"is_parallel": true,
"self": 0.0005196740000315003
},
"communicator.exchange": {
"total": 0.045948535999968954,
"count": 1,
"is_parallel": true,
"self": 0.045948535999968954
},
"steps_from_proto": {
"total": 0.0022302259999946727,
"count": 1,
"is_parallel": true,
"self": 0.00045370300006197795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017765229999326948,
"count": 10,
"is_parallel": true,
"self": 0.0017765229999326948
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 282.67786535500227,
"count": 18191,
"is_parallel": true,
"self": 13.803107265013352,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.5016947939944885,
"count": 18191,
"is_parallel": true,
"self": 7.5016947939944885
},
"communicator.exchange": {
"total": 220.62465627899894,
"count": 18191,
"is_parallel": true,
"self": 220.62465627899894
},
"steps_from_proto": {
"total": 40.748407016995486,
"count": 18191,
"is_parallel": true,
"self": 7.848886990987012,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.899520026008474,
"count": 181910,
"is_parallel": true,
"self": 32.899520026008474
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 164.62566581901086,
"count": 18192,
"self": 0.7942634420214745,
"children": {
"process_trajectory": {
"total": 31.551938158990083,
"count": 18192,
"self": 31.113490052990073,
"children": {
"RLTrainer._checkpoint": {
"total": 0.43844810600000983,
"count": 4,
"self": 0.43844810600000983
}
}
},
"_update_policy": {
"total": 132.2794642179993,
"count": 90,
"self": 49.44085930199202,
"children": {
"TorchPPOOptimizer.update": {
"total": 82.83860491600728,
"count": 4587,
"self": 82.83860491600728
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.471000018682389e-06,
"count": 1,
"self": 1.471000018682389e-06
},
"TrainerController._save_models": {
"total": 0.1124101289999544,
"count": 1,
"self": 0.0013688509999383314,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11104127800001606,
"count": 1,
"self": 0.11104127800001606
}
}
}
}
}
}
}