smartbotfactory's picture
Training 1
6aab22b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8462537527084351,
"min": 0.8453850746154785,
"max": 2.8622097969055176,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8080.03076171875,
"min": 8080.03076171875,
"max": 29311.890625,
"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": 13.00057601928711,
"min": 0.3589330017566681,
"max": 13.113852500915527,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2535.1123046875,
"min": 69.63300323486328,
"max": 2663.41015625,
"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": 0.06711636854953551,
"min": 0.06481044010861832,
"max": 0.07657510829648898,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26846547419814204,
"min": 0.2592417604344733,
"max": 0.3593854484982633,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19909523003825955,
"min": 0.14551064664242314,
"max": 0.28300405822548214,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7963809201530382,
"min": 0.5820425865696925,
"max": 1.4150202911274106,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0776097306000005e-05,
"min": 1.0776097306000005e-05,
"max": 0.000389176002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.310438922400002e-05,
"min": 4.310438922400002e-05,
"max": 0.0018468800382800002,
"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": 25.34090909090909,
"min": 4.0,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 176.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 4.0,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 176.0,
"max": 1422.0,
"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": "1677349301",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677349764"
},
"total": 462.94804303,
"count": 1,
"self": 0.43603144999974575,
"children": {
"run_training.setup": {
"total": 0.10803819000011572,
"count": 1,
"self": 0.10803819000011572
},
"TrainerController.start_learning": {
"total": 462.40397339000015,
"count": 1,
"self": 0.531968835005955,
"children": {
"TrainerController._reset_env": {
"total": 6.647495971000126,
"count": 1,
"self": 6.647495971000126
},
"TrainerController.advance": {
"total": 455.10134636599423,
"count": 18201,
"self": 0.29546375997574614,
"children": {
"env_step": {
"total": 454.8058826060185,
"count": 18201,
"self": 312.7400577150131,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.79270920600584,
"count": 18201,
"self": 1.492527916004292,
"children": {
"TorchPolicy.evaluate": {
"total": 140.30018129000155,
"count": 18201,
"self": 32.09214232199474,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.2080389680068,
"count": 18201,
"self": 108.2080389680068
}
}
}
}
},
"workers": {
"total": 0.27311568499953864,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.85326465100206,
"count": 18201,
"is_parallel": true,
"self": 222.40464536299282,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002166458999909082,
"count": 1,
"is_parallel": true,
"self": 0.0007337959993947152,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001432663000514367,
"count": 10,
"is_parallel": true,
"self": 0.001432663000514367
}
}
},
"UnityEnvironment.step": {
"total": 0.07085184899983688,
"count": 1,
"is_parallel": true,
"self": 0.0005637199999455333,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043455499985611823,
"count": 1,
"is_parallel": true,
"self": 0.00043455499985611823
},
"communicator.exchange": {
"total": 0.06272661200000584,
"count": 1,
"is_parallel": true,
"self": 0.06272661200000584
},
"steps_from_proto": {
"total": 0.00712696200002938,
"count": 1,
"is_parallel": true,
"self": 0.0004569859997900494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0066699760002393305,
"count": 10,
"is_parallel": true,
"self": 0.0066699760002393305
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.44861928800924,
"count": 18200,
"is_parallel": true,
"self": 9.578636193993361,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.243620372008536,
"count": 18200,
"is_parallel": true,
"self": 5.243620372008536
},
"communicator.exchange": {
"total": 192.19858169500344,
"count": 18200,
"is_parallel": true,
"self": 192.19858169500344
},
"steps_from_proto": {
"total": 31.427781027003903,
"count": 18200,
"is_parallel": true,
"self": 6.860696650996033,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.56708437600787,
"count": 182000,
"is_parallel": true,
"self": 24.56708437600787
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001047279999966122,
"count": 1,
"self": 0.0001047279999966122,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 451.58926262702516,
"count": 407177,
"is_parallel": true,
"self": 10.24844690099485,
"children": {
"process_trajectory": {
"total": 258.4086640560306,
"count": 407177,
"is_parallel": true,
"self": 257.63882934703065,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7698347089999515,
"count": 4,
"is_parallel": true,
"self": 0.7698347089999515
}
}
},
"_update_policy": {
"total": 182.9321516699997,
"count": 90,
"is_parallel": true,
"self": 63.90371375900668,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.02843791099303,
"count": 4587,
"is_parallel": true,
"self": 119.02843791099303
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12305748999983734,
"count": 1,
"self": 0.0008856859997194988,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12217180400011785,
"count": 1,
"self": 0.12217180400011785
}
}
}
}
}
}
}