chribeiro's picture
First training of SnowballTarget
3a32c45
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0273001194000244,
"min": 1.0273001194000244,
"max": 2.8715500831604004,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9853.8623046875,
"min": 9853.8623046875,
"max": 29470.71875,
"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": 12.295761108398438,
"min": 0.3548260033130646,
"max": 12.295761108398438,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2397.67333984375,
"min": 68.83624267578125,
"max": 2454.36474609375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06812855972926699,
"min": 0.06088148943221598,
"max": 0.0745425024582016,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27251423891706794,
"min": 0.25928518502862025,
"max": 0.370432829981962,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19919265792065977,
"min": 0.10157077176742914,
"max": 0.2753635677782928,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7967706316826391,
"min": 0.40628308706971655,
"max": 1.3531885781124526,
"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": 24.59090909090909,
"min": 3.0454545454545454,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1082.0,
"min": 134.0,
"max": 1343.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.59090909090909,
"min": 3.0454545454545454,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1082.0,
"min": 134.0,
"max": 1343.0,
"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": "1683258089",
"python_version": "3.10.9 (main, Jan 11 2023, 15:21:40) [GCC 11.2.0]",
"command_line_arguments": "/home/carlos/envs/rl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.0+cu117",
"numpy_version": "1.21.2",
"end_time_seconds": "1683258554"
},
"total": 465.68395847600186,
"count": 1,
"self": 0.2692951000062749,
"children": {
"run_training.setup": {
"total": 0.024012453999603167,
"count": 1,
"self": 0.024012453999603167
},
"TrainerController.start_learning": {
"total": 465.390650921996,
"count": 1,
"self": 0.43166124538402073,
"children": {
"TrainerController._reset_env": {
"total": 1.65937493997626,
"count": 1,
"self": 1.65937493997626
},
"TrainerController.advance": {
"total": 463.22286774765234,
"count": 18204,
"self": 0.1853470585483592,
"children": {
"env_step": {
"total": 463.037520689104,
"count": 18204,
"self": 312.1817546511593,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.64556131701102,
"count": 18204,
"self": 0.9169556649576407,
"children": {
"TorchPolicy.evaluate": {
"total": 149.72860565205337,
"count": 18204,
"self": 149.72860565205337
}
}
},
"workers": {
"total": 0.2102047209336888,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 464.54622375330655,
"count": 18204,
"is_parallel": true,
"self": 213.32977291982388,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0015541629982180893,
"count": 1,
"is_parallel": true,
"self": 0.0004807910299859941,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010733719682320952,
"count": 10,
"is_parallel": true,
"self": 0.0010733719682320952
}
}
},
"UnityEnvironment.step": {
"total": 0.024921956995967776,
"count": 1,
"is_parallel": true,
"self": 0.0002739039482548833,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002448790182825178,
"count": 1,
"is_parallel": true,
"self": 0.0002448790182825178
},
"communicator.exchange": {
"total": 0.02347670801100321,
"count": 1,
"is_parallel": true,
"self": 0.02347670801100321
},
"steps_from_proto": {
"total": 0.0009264660184271634,
"count": 1,
"is_parallel": true,
"self": 0.00017564796144142747,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007508180569857359,
"count": 10,
"is_parallel": true,
"self": 0.0007508180569857359
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.21645083348267,
"count": 18203,
"is_parallel": true,
"self": 5.319748429639731,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.944592583196936,
"count": 18203,
"is_parallel": true,
"self": 2.944592583196936
},
"communicator.exchange": {
"total": 227.20257939392468,
"count": 18203,
"is_parallel": true,
"self": 227.20257939392468
},
"steps_from_proto": {
"total": 15.749530426721321,
"count": 18203,
"is_parallel": true,
"self": 2.951962396968156,
"children": {
"_process_rank_one_or_two_observation": {
"total": 12.797568029753165,
"count": 182030,
"is_parallel": true,
"self": 12.797568029753165
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011254099081270397,
"count": 1,
"self": 0.00011254099081270397,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 461.61094090048573,
"count": 319829,
"is_parallel": true,
"self": 4.861445065733278,
"children": {
"process_trajectory": {
"total": 269.4609872587025,
"count": 319829,
"is_parallel": true,
"self": 268.88798247172963,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5730047869728878,
"count": 4,
"is_parallel": true,
"self": 0.5730047869728878
}
}
},
"_update_policy": {
"total": 187.28850857604994,
"count": 90,
"is_parallel": true,
"self": 32.17790962345316,
"children": {
"TorchPPOOptimizer.update": {
"total": 155.11059895259677,
"count": 4587,
"is_parallel": true,
"self": 155.11059895259677
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07663444799254648,
"count": 1,
"self": 0.0007594739727210253,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07587497401982546,
"count": 1,
"self": 0.07587497401982546
}
}
}
}
}
}
}