Waterboy96's picture
First Push
7f090e9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8382663726806641,
"min": 0.8058270812034607,
"max": 2.8550217151641846,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8612.3486328125,
"min": 7701.3310546875,
"max": 29238.27734375,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.342434883117676,
"min": 0.32510313391685486,
"max": 13.368542671203613,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2721.856689453125,
"min": 63.07000732421875,
"max": 2740.55126953125,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06767442978875182,
"min": 0.06096500672477609,
"max": 0.07553878277961784,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3383721489437591,
"min": 0.24386002689910435,
"max": 0.3675082893368752,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17273458452785714,
"min": 0.130517509542223,
"max": 0.2989084209881577,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8636729226392857,
"min": 0.522070038168892,
"max": 1.4945421049407883,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.050764903999999e-06,
"min": 7.050764903999999e-06,
"max": 0.00039278400180400006,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.5253824519999994e-05,
"min": 3.5253824519999994e-05,
"max": 0.0018979200255199997,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10176266666666667,
"min": 0.10176266666666667,
"max": 0.198196,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5088133333333333,
"min": 0.42025066666666666,
"max": 0.97448,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.795706666666662e-05,
"min": 9.795706666666662e-05,
"max": 0.0049099804000000006,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004897853333333331,
"min": 0.0004897853333333331,
"max": 0.023726551999999998,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.12727272727273,
"min": 3.477272727272727,
"max": 26.527272727272727,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1437.0,
"min": 153.0,
"max": 1459.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.12727272727273,
"min": 3.477272727272727,
"max": 26.527272727272727,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1437.0,
"min": 153.0,
"max": 1459.0,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674958489",
"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": "1.21.6",
"end_time_seconds": "1674959127"
},
"total": 638.672436513,
"count": 1,
"self": 0.4071399809998866,
"children": {
"run_training.setup": {
"total": 0.10362947400000166,
"count": 1,
"self": 0.10362947400000166
},
"TrainerController.start_learning": {
"total": 638.161667058,
"count": 1,
"self": 0.805001895988994,
"children": {
"TrainerController._reset_env": {
"total": 9.318085512999971,
"count": 1,
"self": 9.318085512999971
},
"TrainerController.advance": {
"total": 627.9182974670111,
"count": 27335,
"self": 0.41728096701592676,
"children": {
"env_step": {
"total": 627.5010164999952,
"count": 27335,
"self": 411.3991770439772,
"children": {
"SubprocessEnvManager._take_step": {
"total": 215.69254540401005,
"count": 27335,
"self": 2.073635491016546,
"children": {
"TorchPolicy.evaluate": {
"total": 213.6189099129935,
"count": 27335,
"self": 47.27130729298926,
"children": {
"TorchPolicy.sample_actions": {
"total": 166.34760262000424,
"count": 27335,
"self": 166.34760262000424
}
}
}
}
},
"workers": {
"total": 0.4092940520079651,
"count": 27335,
"self": 0.0,
"children": {
"worker_root": {
"total": 636.3681727930021,
"count": 27335,
"is_parallel": true,
"self": 306.40924337798725,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005435481999995773,
"count": 1,
"is_parallel": true,
"self": 0.0030366320000325686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002398849999963204,
"count": 10,
"is_parallel": true,
"self": 0.002398849999963204
}
}
},
"UnityEnvironment.step": {
"total": 0.03880889399999887,
"count": 1,
"is_parallel": true,
"self": 0.0005176669999968908,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035398099998928956,
"count": 1,
"is_parallel": true,
"self": 0.00035398099998928956
},
"communicator.exchange": {
"total": 0.03590504900000724,
"count": 1,
"is_parallel": true,
"self": 0.03590504900000724
},
"steps_from_proto": {
"total": 0.0020321970000054534,
"count": 1,
"is_parallel": true,
"self": 0.0005025650000902715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001529631999915182,
"count": 10,
"is_parallel": true,
"self": 0.001529631999915182
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 329.9589294150149,
"count": 27334,
"is_parallel": true,
"self": 12.444956536016036,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.49288862200018,
"count": 27334,
"is_parallel": true,
"self": 7.49288862200018
},
"communicator.exchange": {
"total": 264.46869374098895,
"count": 27334,
"is_parallel": true,
"self": 264.46869374098895
},
"steps_from_proto": {
"total": 45.55239051600972,
"count": 27334,
"is_parallel": true,
"self": 9.697409097010791,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.85498141899893,
"count": 273340,
"is_parallel": true,
"self": 35.85498141899893
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.934999995180988e-05,
"count": 1,
"self": 3.934999995180988e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 623.6325648380146,
"count": 496453,
"is_parallel": true,
"self": 13.42326720298638,
"children": {
"process_trajectory": {
"total": 358.25313401802794,
"count": 496453,
"is_parallel": true,
"self": 357.1426294610278,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1105045570001266,
"count": 6,
"is_parallel": true,
"self": 1.1105045570001266
}
}
},
"_update_policy": {
"total": 251.9561636170002,
"count": 136,
"is_parallel": true,
"self": 59.63447762899847,
"children": {
"TorchPPOOptimizer.update": {
"total": 192.32168598800172,
"count": 6933,
"is_parallel": true,
"self": 192.32168598800172
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12024283200003083,
"count": 1,
"self": 0.00115583499996319,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11908699700006764,
"count": 1,
"self": 0.11908699700006764
}
}
}
}
}
}
}