dumuguo's picture
First Push
86b09c7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.72683185338974,
"min": 0.72683185338974,
"max": 2.8574867248535156,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6907.81005859375,
"min": 6907.81005859375,
"max": 29169.224609375,
"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": 13.086570739746094,
"min": 0.2537533640861511,
"max": 13.16429615020752,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2551.88134765625,
"min": 49.228153228759766,
"max": 2670.237060546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06790195021301984,
"min": 0.06129335406762502,
"max": 0.07924344570321196,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27160780085207936,
"min": 0.24517341627050007,
"max": 0.3962172285160598,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19492506411145716,
"min": 0.10182698921633739,
"max": 0.28274763156385985,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7797002564458286,
"min": 0.40730795686534954,
"max": 1.4137381578192991,
"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": 25.613636363636363,
"min": 2.7045454545454546,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 119.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 2.7045454545454546,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 119.0,
"max": 1423.0,
"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": "1751516079",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751516650"
},
"total": 571.2138752500005,
"count": 1,
"self": 0.5467378590010412,
"children": {
"run_training.setup": {
"total": 0.04184418499971798,
"count": 1,
"self": 0.04184418499971798
},
"TrainerController.start_learning": {
"total": 570.6252932059997,
"count": 1,
"self": 0.5887290480377487,
"children": {
"TrainerController._reset_env": {
"total": 4.984070395999879,
"count": 1,
"self": 4.984070395999879
},
"TrainerController.advance": {
"total": 564.974351391962,
"count": 18192,
"self": 0.6985192259962787,
"children": {
"env_step": {
"total": 396.201346470938,
"count": 18192,
"self": 340.3587478870495,
"children": {
"SubprocessEnvManager._take_step": {
"total": 55.461217902909084,
"count": 18192,
"self": 2.0521133929814823,
"children": {
"TorchPolicy.evaluate": {
"total": 53.4091045099276,
"count": 18192,
"self": 53.4091045099276
}
}
},
"workers": {
"total": 0.3813806809794187,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 568.323938743968,
"count": 18192,
"is_parallel": true,
"self": 275.16274377706395,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.01005442700079584,
"count": 1,
"is_parallel": true,
"self": 0.006996222999987367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003058204000808473,
"count": 10,
"is_parallel": true,
"self": 0.003058204000808473
}
}
},
"UnityEnvironment.step": {
"total": 0.10759023699938552,
"count": 1,
"is_parallel": true,
"self": 0.0007662769994567498,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004568009999275091,
"count": 1,
"is_parallel": true,
"self": 0.0004568009999275091
},
"communicator.exchange": {
"total": 0.10187530999974115,
"count": 1,
"is_parallel": true,
"self": 0.10187530999974115
},
"steps_from_proto": {
"total": 0.0044918490002601175,
"count": 1,
"is_parallel": true,
"self": 0.0027082750011686585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001783573999091459,
"count": 10,
"is_parallel": true,
"self": 0.001783573999091459
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 293.1611949669041,
"count": 18191,
"is_parallel": true,
"self": 14.108073273998343,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.398521673981122,
"count": 18191,
"is_parallel": true,
"self": 7.398521673981122
},
"communicator.exchange": {
"total": 230.36148052396948,
"count": 18191,
"is_parallel": true,
"self": 230.36148052396948
},
"steps_from_proto": {
"total": 41.293119494955135,
"count": 18191,
"is_parallel": true,
"self": 7.980485431010493,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.31263406394464,
"count": 181910,
"is_parallel": true,
"self": 33.31263406394464
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 168.07448569502776,
"count": 18192,
"self": 0.8828245349823192,
"children": {
"process_trajectory": {
"total": 32.43480319304854,
"count": 18192,
"self": 31.92114685904835,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5136563340001885,
"count": 4,
"self": 0.5136563340001885
}
}
},
"_update_policy": {
"total": 134.7568579669969,
"count": 90,
"self": 52.58170141197024,
"children": {
"TorchPPOOptimizer.update": {
"total": 82.17515655502666,
"count": 4587,
"self": 82.17515655502666
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0309995559509844e-06,
"count": 1,
"self": 1.0309995559509844e-06
},
"TrainerController._save_models": {
"total": 0.07814133900046727,
"count": 1,
"self": 0.0011328580003464594,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07700848100012081,
"count": 1,
"self": 0.07700848100012081
}
}
}
}
}
}
}