Lanzp's picture
First Push
764ac0f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7069336771965027,
"min": 0.7069336771965027,
"max": 2.852567195892334,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6718.69775390625,
"min": 6718.69775390625,
"max": 29119.005859375,
"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": 12.962030410766602,
"min": 0.34002622961997986,
"max": 12.962030410766602,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2527.595947265625,
"min": 65.965087890625,
"max": 2626.02880859375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06737603673508263,
"min": 0.060983895285593746,
"max": 0.07200152207195631,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26950414694033054,
"min": 0.2517786411164493,
"max": 0.35703297863102645,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19961119896056606,
"min": 0.1127260921879069,
"max": 0.2659792963634519,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7984447958422642,
"min": 0.4509043687516276,
"max": 1.318580755123905,
"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": 25.90909090909091,
"min": 3.227272727272727,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1140.0,
"min": 142.0,
"max": 1398.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.90909090909091,
"min": 3.227272727272727,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1140.0,
"min": 142.0,
"max": 1398.0,
"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": "1745112196",
"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": "1745112626"
},
"total": 429.859785872,
"count": 1,
"self": 0.4338822089999894,
"children": {
"run_training.setup": {
"total": 0.03222872800000687,
"count": 1,
"self": 0.03222872800000687
},
"TrainerController.start_learning": {
"total": 429.393674935,
"count": 1,
"self": 0.35397160299828556,
"children": {
"TrainerController._reset_env": {
"total": 3.0574870649999752,
"count": 1,
"self": 3.0574870649999752
},
"TrainerController.advance": {
"total": 425.8965569360016,
"count": 18192,
"self": 0.36345698298202933,
"children": {
"env_step": {
"total": 303.1347684860155,
"count": 18192,
"self": 230.11883460401907,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.81203921399828,
"count": 18192,
"self": 1.2894836850057345,
"children": {
"TorchPolicy.evaluate": {
"total": 71.52255552899254,
"count": 18192,
"self": 71.52255552899254
}
}
},
"workers": {
"total": 0.20389466799815636,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.997812352001,
"count": 18192,
"is_parallel": true,
"self": 225.99735944500486,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005901825000023564,
"count": 1,
"is_parallel": true,
"self": 0.004219185000067682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016826399999558816,
"count": 10,
"is_parallel": true,
"self": 0.0016826399999558816
}
}
},
"UnityEnvironment.step": {
"total": 0.03659783900002367,
"count": 1,
"is_parallel": true,
"self": 0.000615283999991334,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000400205999994796,
"count": 1,
"is_parallel": true,
"self": 0.000400205999994796
},
"communicator.exchange": {
"total": 0.03373137700003781,
"count": 1,
"is_parallel": true,
"self": 0.03373137700003781
},
"steps_from_proto": {
"total": 0.0018509719999997287,
"count": 1,
"is_parallel": true,
"self": 0.000348732999952972,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015022390000467567,
"count": 10,
"is_parallel": true,
"self": 0.0015022390000467567
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.00045290699614,
"count": 18191,
"is_parallel": true,
"self": 9.978947836004977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.432360093993509,
"count": 18191,
"is_parallel": true,
"self": 5.432360093993509
},
"communicator.exchange": {
"total": 153.97034099700141,
"count": 18191,
"is_parallel": true,
"self": 153.97034099700141
},
"steps_from_proto": {
"total": 32.618803979996244,
"count": 18191,
"is_parallel": true,
"self": 5.869327446982425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.74947653301382,
"count": 181910,
"is_parallel": true,
"self": 26.74947653301382
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.39833146700408,
"count": 18192,
"self": 0.44032221000225036,
"children": {
"process_trajectory": {
"total": 27.3747723560017,
"count": 18192,
"self": 26.94622986600166,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42854249000004074,
"count": 4,
"self": 0.42854249000004074
}
}
},
"_update_policy": {
"total": 94.58323690100013,
"count": 90,
"self": 37.80835245799926,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.77488444300087,
"count": 4587,
"self": 56.77488444300087
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0800000609378912e-06,
"count": 1,
"self": 1.0800000609378912e-06
},
"TrainerController._save_models": {
"total": 0.08565825100004076,
"count": 1,
"self": 0.000815091000049506,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08484315999999126,
"count": 1,
"self": 0.08484315999999126
}
}
}
}
}
}
}