kelestemur's picture
First Push
7085617
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9029732942581177,
"min": 0.9029732942581177,
"max": 2.8534579277038574,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8621.5888671875,
"min": 8621.5888671875,
"max": 29222.26171875,
"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": 12.800443649291992,
"min": 0.49838733673095703,
"max": 12.800443649291992,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2496.08642578125,
"min": 96.68714141845703,
"max": 2579.615966796875,
"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": 0.06451238683689108,
"min": 0.06343656149842633,
"max": 0.07123537240123351,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2580495473475643,
"min": 0.2537462459937053,
"max": 0.35617686200616755,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20311734708500845,
"min": 0.14175513477575985,
"max": 0.29175240086282,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8124693883400338,
"min": 0.5670205391030394,
"max": 1.3927407927957236,
"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": 25.227272727272727,
"min": 3.9318181818181817,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 173.0,
"max": 1380.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.9318181818181817,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 173.0,
"max": 1380.0,
"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": "1678067223",
"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 --force ./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": "1678067728"
},
"total": 505.21412692600006,
"count": 1,
"self": 0.4359351210000568,
"children": {
"run_training.setup": {
"total": 0.11478052699999353,
"count": 1,
"self": 0.11478052699999353
},
"TrainerController.start_learning": {
"total": 504.663411278,
"count": 1,
"self": 0.6725639450130529,
"children": {
"TrainerController._reset_env": {
"total": 6.3966304399998535,
"count": 1,
"self": 6.3966304399998535
},
"TrainerController.advance": {
"total": 497.4588790899868,
"count": 18202,
"self": 0.36687072999438897,
"children": {
"env_step": {
"total": 497.0920083599924,
"count": 18202,
"self": 343.6140730340139,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.14412920200357,
"count": 18202,
"self": 1.7081767290085281,
"children": {
"TorchPolicy.evaluate": {
"total": 151.43595247299504,
"count": 18202,
"self": 34.697368721978364,
"children": {
"TorchPolicy.sample_actions": {
"total": 116.73858375101668,
"count": 18202,
"self": 116.73858375101668
}
}
}
}
},
"workers": {
"total": 0.3338061239749095,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 502.8741262080109,
"count": 18202,
"is_parallel": true,
"self": 239.08990265099487,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026571240000521357,
"count": 1,
"is_parallel": true,
"self": 0.0009360209999158542,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017211030001362815,
"count": 10,
"is_parallel": true,
"self": 0.0017211030001362815
}
}
},
"UnityEnvironment.step": {
"total": 0.06258308299993587,
"count": 1,
"is_parallel": true,
"self": 0.0006194109998887143,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039934100004757056,
"count": 1,
"is_parallel": true,
"self": 0.00039934100004757056
},
"communicator.exchange": {
"total": 0.059480868000036935,
"count": 1,
"is_parallel": true,
"self": 0.059480868000036935
},
"steps_from_proto": {
"total": 0.0020834629999626486,
"count": 1,
"is_parallel": true,
"self": 0.0006735890003710665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001409873999591582,
"count": 10,
"is_parallel": true,
"self": 0.001409873999591582
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 263.78422355701605,
"count": 18201,
"is_parallel": true,
"self": 10.213407149017257,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.763721465990329,
"count": 18201,
"is_parallel": true,
"self": 5.763721465990329
},
"communicator.exchange": {
"total": 212.46295004100625,
"count": 18201,
"is_parallel": true,
"self": 212.46295004100625
},
"steps_from_proto": {
"total": 35.34414490100221,
"count": 18201,
"is_parallel": true,
"self": 8.243218748029904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.100926152972306,
"count": 182010,
"is_parallel": true,
"self": 27.100926152972306
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012827700015805021,
"count": 1,
"self": 0.00012827700015805021,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 493.7301763710375,
"count": 439755,
"is_parallel": true,
"self": 11.257414517120878,
"children": {
"process_trajectory": {
"total": 283.29787515991666,
"count": 439755,
"is_parallel": true,
"self": 282.4933708249166,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8045043350000469,
"count": 4,
"is_parallel": true,
"self": 0.8045043350000469
}
}
},
"_update_policy": {
"total": 199.17488669399995,
"count": 90,
"is_parallel": true,
"self": 69.05733562000864,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.1175510739913,
"count": 4587,
"is_parallel": true,
"self": 130.1175510739913
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13520952600015335,
"count": 1,
"self": 0.0011721420003141247,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13403738399983922,
"count": 1,
"self": 0.13403738399983922
}
}
}
}
}
}
}