carlosq's picture
Second Push
89684ab verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0019701719284058,
"min": 1.0019701719284058,
"max": 2.8738925457000732,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9566.8115234375,
"min": 9566.8115234375,
"max": 29526.37109375,
"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": 12.924033164978027,
"min": 0.3537145256996155,
"max": 12.924033164978027,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.1865234375,
"min": 68.62062072753906,
"max": 2603.72119140625,
"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.Losses.PolicyLoss.mean": {
"value": 0.06724965259424572,
"min": 0.06089129457056212,
"max": 0.07462373430935972,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26899861037698286,
"min": 0.24356517828224847,
"max": 0.37311867154679856,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17851804160312107,
"min": 0.1296411275603425,
"max": 0.27650778652990565,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7140721664124843,
"min": 0.51856451024137,
"max": 1.2984937029142003,
"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.CumulativeReward.mean": {
"value": 25.681818181818183,
"min": 3.5,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 154.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 3.5,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 154.0,
"max": 1397.0,
"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": "1717508987",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717509438"
},
"total": 450.950478869,
"count": 1,
"self": 0.43460661799997524,
"children": {
"run_training.setup": {
"total": 0.08434326999997666,
"count": 1,
"self": 0.08434326999997666
},
"TrainerController.start_learning": {
"total": 450.43152898100004,
"count": 1,
"self": 0.5677419910022081,
"children": {
"TrainerController._reset_env": {
"total": 3.3792666759999292,
"count": 1,
"self": 3.3792666759999292
},
"TrainerController.advance": {
"total": 446.396478768998,
"count": 18201,
"self": 0.28037120098917967,
"children": {
"env_step": {
"total": 446.11610756800883,
"count": 18201,
"self": 291.4872458690098,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.34312965199626,
"count": 18201,
"self": 1.4598988950075409,
"children": {
"TorchPolicy.evaluate": {
"total": 152.88323075698872,
"count": 18201,
"self": 152.88323075698872
}
}
},
"workers": {
"total": 0.2857320470027389,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.3060285460001,
"count": 18201,
"is_parallel": true,
"self": 226.424932869999,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006582831000059741,
"count": 1,
"is_parallel": true,
"self": 0.004122744000028433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002460087000031308,
"count": 10,
"is_parallel": true,
"self": 0.002460087000031308
}
}
},
"UnityEnvironment.step": {
"total": 0.03619192799999382,
"count": 1,
"is_parallel": true,
"self": 0.0006816950000256838,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003891349999776139,
"count": 1,
"is_parallel": true,
"self": 0.0003891349999776139
},
"communicator.exchange": {
"total": 0.03317099999992479,
"count": 1,
"is_parallel": true,
"self": 0.03317099999992479
},
"steps_from_proto": {
"total": 0.0019500980000657364,
"count": 1,
"is_parallel": true,
"self": 0.00036032000048180635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00158977799958393,
"count": 10,
"is_parallel": true,
"self": 0.00158977799958393
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 222.8810956760011,
"count": 18200,
"is_parallel": true,
"self": 10.29917420699303,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.364845220000575,
"count": 18200,
"is_parallel": true,
"self": 5.364845220000575
},
"communicator.exchange": {
"total": 174.0986276730075,
"count": 18200,
"is_parallel": true,
"self": 174.0986276730075
},
"steps_from_proto": {
"total": 33.11844857599999,
"count": 18200,
"is_parallel": true,
"self": 6.269228363018669,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.849220212981322,
"count": 182000,
"is_parallel": true,
"self": 26.849220212981322
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011540199989212852,
"count": 1,
"self": 0.00011540199989212852,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 441.0731136010006,
"count": 668774,
"is_parallel": true,
"self": 13.878266203965268,
"children": {
"process_trajectory": {
"total": 243.748400845035,
"count": 668774,
"is_parallel": true,
"self": 243.0441920840351,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7042087609999044,
"count": 4,
"is_parallel": true,
"self": 0.7042087609999044
}
}
},
"_update_policy": {
"total": 183.44644655200034,
"count": 90,
"is_parallel": true,
"self": 59.76644125400003,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.68000529800031,
"count": 4587,
"is_parallel": true,
"self": 123.68000529800031
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08792614300000423,
"count": 1,
"self": 0.000969076000046698,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08695706699995753,
"count": 1,
"self": 0.08695706699995753
}
}
}
}
}
}
}