wowthecoder's picture
Second test run
854acd9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7578401565551758,
"min": 0.7578401565551758,
"max": 2.8495936393737793,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7202.5126953125,
"min": 7202.5126953125,
"max": 29088.65234375,
"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": 13.306885719299316,
"min": 0.5077546238899231,
"max": 13.497345924377441,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2594.8427734375,
"min": 98.50440216064453,
"max": 2752.75,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.043117407193979794,
"min": 0.041890770931180064,
"max": 0.05512676508321117,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.17246962877591918,
"min": 0.16756308372472026,
"max": 0.2595114825120011,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1955135907046497,
"min": 0.1359500007238239,
"max": 0.3003390124067664,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7820543628185987,
"min": 0.5438000028952956,
"max": 1.3857900959750016,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.694009730600002e-05,
"min": 2.694009730600002e-05,
"max": 0.000972940002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00010776038922400007,
"min": 0.00010776038922400007,
"max": 0.004617200038280001,
"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": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"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": 26.045454545454547,
"min": 3.8181818181818183,
"max": 27.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1146.0,
"min": 168.0,
"max": 1442.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.045454545454547,
"min": 3.8181818181818183,
"max": 27.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1146.0,
"min": 168.0,
"max": 1442.0,
"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": "1737245876",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1737246234"
},
"total": 358.2258431539999,
"count": 1,
"self": 0.3292246050000358,
"children": {
"run_training.setup": {
"total": 0.08340822799982561,
"count": 1,
"self": 0.08340822799982561
},
"TrainerController.start_learning": {
"total": 357.81321032100004,
"count": 1,
"self": 0.3241159759841139,
"children": {
"TrainerController._reset_env": {
"total": 4.709884568999769,
"count": 1,
"self": 4.709884568999769
},
"TrainerController.advance": {
"total": 352.6907825740159,
"count": 18192,
"self": 0.34657970504622426,
"children": {
"env_step": {
"total": 265.89916335997304,
"count": 18192,
"self": 200.5090012449673,
"children": {
"SubprocessEnvManager._take_step": {
"total": 65.18958782399386,
"count": 18192,
"self": 1.1350779470126326,
"children": {
"TorchPolicy.evaluate": {
"total": 64.05450987698123,
"count": 18192,
"self": 64.05450987698123
}
}
},
"workers": {
"total": 0.20057429101188973,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 357.07193339096693,
"count": 18192,
"is_parallel": true,
"self": 180.6356780869387,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002237651000086771,
"count": 1,
"is_parallel": true,
"self": 0.0006449709999287734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015926800001579977,
"count": 10,
"is_parallel": true,
"self": 0.0015926800001579977
}
}
},
"UnityEnvironment.step": {
"total": 0.027012511000066297,
"count": 1,
"is_parallel": true,
"self": 0.00041847700003927457,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000266099000327813,
"count": 1,
"is_parallel": true,
"self": 0.000266099000327813
},
"communicator.exchange": {
"total": 0.025165166999613575,
"count": 1,
"is_parallel": true,
"self": 0.025165166999613575
},
"steps_from_proto": {
"total": 0.0011627680000856344,
"count": 1,
"is_parallel": true,
"self": 0.00024115799942592275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009216100006597117,
"count": 10,
"is_parallel": true,
"self": 0.0009216100006597117
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 176.43625530402824,
"count": 18191,
"is_parallel": true,
"self": 7.640120969095278,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.085226885965767,
"count": 18191,
"is_parallel": true,
"self": 4.085226885965767
},
"communicator.exchange": {
"total": 139.61412439696232,
"count": 18191,
"is_parallel": true,
"self": 139.61412439696232
},
"steps_from_proto": {
"total": 25.096783052004866,
"count": 18191,
"is_parallel": true,
"self": 4.764068768921788,
"children": {
"_process_rank_one_or_two_observation": {
"total": 20.332714283083078,
"count": 181910,
"is_parallel": true,
"self": 20.332714283083078
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 86.44503950899662,
"count": 18192,
"self": 0.3822299280068364,
"children": {
"process_trajectory": {
"total": 25.07527838098804,
"count": 18192,
"self": 24.657987443987622,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4172909370004163,
"count": 4,
"self": 0.4172909370004163
}
}
},
"_update_policy": {
"total": 60.98753120000174,
"count": 90,
"self": 34.6922201549969,
"children": {
"TorchPPOOptimizer.update": {
"total": 26.295311045004837,
"count": 2160,
"self": 26.295311045004837
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.609999895270448e-07,
"count": 1,
"self": 8.609999895270448e-07
},
"TrainerController._save_models": {
"total": 0.0884263410002859,
"count": 1,
"self": 0.0009129190002568066,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0875134220000291,
"count": 1,
"self": 0.0875134220000291
}
}
}
}
}
}
}