ajinkyag24's picture
First Trial Push
9afa97b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0988794565200806,
"min": 1.0969693660736084,
"max": 2.874493360519409,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10443.75,
"min": 10443.75,
"max": 29342.828125,
"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": 11.793705940246582,
"min": 0.23338642716407776,
"max": 11.793705940246582,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2299.772705078125,
"min": 45.2769660949707,
"max": 2391.6943359375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.09152474384570145,
"min": 0.09152474384570145,
"max": 0.1041018409598787,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3660989753828058,
"min": 0.3660989753828058,
"max": 0.5205092047993936,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2191854621119359,
"min": 0.11594279921700514,
"max": 0.27004174110205736,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8767418484477436,
"min": 0.46377119686802054,
"max": 1.2296570628589274,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.6940973060000016e-06,
"min": 2.6940973060000016e-06,
"max": 9.729400270600002e-05,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0776389224000007e-05,
"min": 1.0776389224000007e-05,
"max": 0.00046172003828000015,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999997,
"min": 0.10269399999999997,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077599999999986,
"min": 0.41077599999999986,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828000000003,
"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": 23.15909090909091,
"min": 3.2954545454545454,
"max": 23.472727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1019.0,
"min": 145.0,
"max": 1291.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.15909090909091,
"min": 3.2954545454545454,
"max": 23.472727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1019.0,
"min": 145.0,
"max": 1291.0,
"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": "1744789377",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744789881"
},
"total": 503.903213454,
"count": 1,
"self": 0.4384103240000172,
"children": {
"run_training.setup": {
"total": 0.024008288999993965,
"count": 1,
"self": 0.024008288999993965
},
"TrainerController.start_learning": {
"total": 503.440794841,
"count": 1,
"self": 0.4493466649959146,
"children": {
"TrainerController._reset_env": {
"total": 3.047074556000041,
"count": 1,
"self": 3.047074556000041
},
"TrainerController.advance": {
"total": 499.844794514004,
"count": 18192,
"self": 0.42332374499824255,
"children": {
"env_step": {
"total": 319.4954743070087,
"count": 18192,
"self": 243.15831214401135,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.08118667099399,
"count": 18192,
"self": 1.44188578099795,
"children": {
"TorchPolicy.evaluate": {
"total": 74.63930088999604,
"count": 18192,
"self": 74.63930088999604
}
}
},
"workers": {
"total": 0.25597549200335834,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 501.8924766189945,
"count": 18192,
"is_parallel": true,
"self": 289.82254969298646,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006147671999997328,
"count": 1,
"is_parallel": true,
"self": 0.004598647999955574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015490240000417543,
"count": 10,
"is_parallel": true,
"self": 0.0015490240000417543
}
}
},
"UnityEnvironment.step": {
"total": 0.04461085700000922,
"count": 1,
"is_parallel": true,
"self": 0.0005705589999820404,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042715600000065024,
"count": 1,
"is_parallel": true,
"self": 0.00042715600000065024
},
"communicator.exchange": {
"total": 0.03959161900002073,
"count": 1,
"is_parallel": true,
"self": 0.03959161900002073
},
"steps_from_proto": {
"total": 0.0040215230000058,
"count": 1,
"is_parallel": true,
"self": 0.00039354799997681766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0036279750000289823,
"count": 10,
"is_parallel": true,
"self": 0.0036279750000289823
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.06992692600807,
"count": 18191,
"is_parallel": true,
"self": 10.042535542026314,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.4960518189996606,
"count": 18191,
"is_parallel": true,
"self": 5.4960518189996606
},
"communicator.exchange": {
"total": 163.92766731499285,
"count": 18191,
"is_parallel": true,
"self": 163.92766731499285
},
"steps_from_proto": {
"total": 32.603672249989245,
"count": 18191,
"is_parallel": true,
"self": 6.069817828023872,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.533854421965373,
"count": 181910,
"is_parallel": true,
"self": 26.533854421965373
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 179.92599646199704,
"count": 18192,
"self": 0.556468441001357,
"children": {
"process_trajectory": {
"total": 28.031284357996356,
"count": 18192,
"self": 27.58921788899636,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4420664689999967,
"count": 4,
"self": 0.4420664689999967
}
}
},
"_update_policy": {
"total": 151.33824366299933,
"count": 90,
"self": 39.99359118499933,
"children": {
"TorchPPOOptimizer.update": {
"total": 111.344652478,
"count": 9177,
"self": 111.344652478
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.002000090011279e-06,
"count": 1,
"self": 1.002000090011279e-06
},
"TrainerController._save_models": {
"total": 0.09957810399998834,
"count": 1,
"self": 0.0009426219999113528,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09863548200007699,
"count": 1,
"self": 0.09863548200007699
}
}
}
}
}
}
}