qb1t's picture
First Push
4edbdc0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.810280442237854,
"min": 0.810280442237854,
"max": 2.837357997894287,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7700.9052734375,
"min": 7700.9052734375,
"max": 28963.75,
"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": 13.275604248046875,
"min": 0.3401055335998535,
"max": 13.275604248046875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2588.742919921875,
"min": 65.98047637939453,
"max": 2707.98876953125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06916197806447813,
"min": 0.06183836239159814,
"max": 0.07382847890760019,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2766479122579125,
"min": 0.24805288484112323,
"max": 0.3676098028158509,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1940061646130155,
"min": 0.1316372391496164,
"max": 0.3064338608115327,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.776024658452062,
"min": 0.5265489565984656,
"max": 1.5321693040576634,
"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": 25.772727272727273,
"min": 3.5454545454545454,
"max": 26.12727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 156.0,
"max": 1437.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.5454545454545454,
"max": 26.12727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 156.0,
"max": 1437.0,
"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": "1773701978",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1773702130"
},
"total": 151.70360534399993,
"count": 1,
"self": 0.16675553799996123,
"children": {
"run_training.setup": {
"total": 0.010002669999948921,
"count": 1,
"self": 0.010002669999948921
},
"TrainerController.start_learning": {
"total": 151.52684713600001,
"count": 1,
"self": 0.1394005820379789,
"children": {
"TrainerController._reset_env": {
"total": 1.248228356000027,
"count": 1,
"self": 1.248228356000027
},
"TrainerController.advance": {
"total": 150.1108484479621,
"count": 18192,
"self": 0.13323618996469122,
"children": {
"env_step": {
"total": 105.25907748900022,
"count": 18192,
"self": 81.75320251497965,
"children": {
"SubprocessEnvManager._take_step": {
"total": 23.41208353000502,
"count": 18192,
"self": 0.5117203470083496,
"children": {
"TorchPolicy.evaluate": {
"total": 22.90036318299667,
"count": 18192,
"self": 22.90036318299667
}
}
},
"workers": {
"total": 0.09379144401555095,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 151.19401059798133,
"count": 18192,
"is_parallel": true,
"self": 78.5743339119822,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007553899999948044,
"count": 1,
"is_parallel": true,
"self": 0.00020899999981338624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005463900001814181,
"count": 10,
"is_parallel": true,
"self": 0.0005463900001814181
}
}
},
"UnityEnvironment.step": {
"total": 0.013253399000177524,
"count": 1,
"is_parallel": true,
"self": 0.00015645000030417577,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001590500000929751,
"count": 1,
"is_parallel": true,
"self": 0.0001590500000929751
},
"communicator.exchange": {
"total": 0.012462518999882377,
"count": 1,
"is_parallel": true,
"self": 0.012462518999882377
},
"steps_from_proto": {
"total": 0.00047537999989799573,
"count": 1,
"is_parallel": true,
"self": 0.00012049999941154965,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003548800004864461,
"count": 10,
"is_parallel": true,
"self": 0.0003548800004864461
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 72.61967668599914,
"count": 18191,
"is_parallel": true,
"self": 2.2595492110431223,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.1262106979863802,
"count": 18191,
"is_parallel": true,
"self": 1.1262106979863802
},
"communicator.exchange": {
"total": 62.68402922698965,
"count": 18191,
"is_parallel": true,
"self": 62.68402922698965
},
"steps_from_proto": {
"total": 6.549887549979985,
"count": 18191,
"is_parallel": true,
"self": 1.17070637302686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 5.379181176953125,
"count": 181910,
"is_parallel": true,
"self": 5.379181176953125
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 44.71853476899719,
"count": 18192,
"self": 0.16118251400985173,
"children": {
"process_trajectory": {
"total": 10.239170049987706,
"count": 18192,
"self": 10.107224051987941,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13194599799976459,
"count": 4,
"self": 0.13194599799976459
}
}
},
"_update_policy": {
"total": 34.31818220499963,
"count": 90,
"self": 15.275723312998252,
"children": {
"TorchPPOOptimizer.update": {
"total": 19.042458892001378,
"count": 4587,
"self": 19.042458892001378
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.999999525054591e-07,
"count": 1,
"self": 7.999999525054591e-07
},
"TrainerController._save_models": {
"total": 0.028368949999958204,
"count": 1,
"self": 0.00029131999986020674,
"children": {
"RLTrainer._checkpoint": {
"total": 0.028077630000097997,
"count": 1,
"self": 0.028077630000097997
}
}
}
}
}
}
}