aronmal's picture
First Push
ae05126
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.996075451374054,
"min": 0.996075451374054,
"max": 2.860722541809082,
"count": 28
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9663.923828125,
"min": 9663.923828125,
"max": 29391.0625,
"count": 28
},
"SnowballTarget.Step.mean": {
"value": 279976.0,
"min": 9952.0,
"max": 279976.0,
"count": 28
},
"SnowballTarget.Step.sum": {
"value": 279976.0,
"min": 9952.0,
"max": 279976.0,
"count": 28
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.579413414001465,
"min": 0.5690706372261047,
"max": 13.579413414001465,
"count": 28
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2783.77978515625,
"min": 110.39970397949219,
"max": 2783.77978515625,
"count": 28
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 28
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 28
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07658176147356155,
"min": 0.06180642449192009,
"max": 0.07658176147356155,
"count": 28
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.38290880736780775,
"min": 0.26769076841518136,
"max": 0.38290880736780775,
"count": 28
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17232125112239052,
"min": 0.1653258486705668,
"max": 0.26272045769820024,
"count": 28
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8616062556119526,
"min": 0.6683721109932543,
"max": 1.303909688895824,
"count": 28
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.0004501760549823999,
"min": 0.0004501760549823999,
"max": 0.0009891760010824,
"count": 28
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0022508802749119997,
"min": 0.0018799042120096,
"max": 0.0048468800153119995,
"count": 28
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.14501760000000002,
"min": 0.14501760000000002,
"max": 0.19891759999999997,
"count": 28
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.7250880000000001,
"min": 0.5879904,
"max": 0.984688,
"count": 28
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0022563782400000006,
"min": 0.0022563782400000006,
"max": 0.00494598824,
"count": 28
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.011281891200000003,
"min": 0.00942072096,
"max": 0.0242359312,
"count": 28
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.89090909090909,
"min": 4.886363636363637,
"max": 26.954545454545453,
"count": 28
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1479.0,
"min": 215.0,
"max": 1479.0,
"count": 28
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.89090909090909,
"min": 4.886363636363637,
"max": 26.954545454545453,
"count": 28
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1479.0,
"min": 215.0,
"max": 1479.0,
"count": 28
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 28
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 28
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688721709",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688722457"
},
"total": 748.169318858,
"count": 1,
"self": 0.19765631699988262,
"children": {
"run_training.setup": {
"total": 0.03759667700001046,
"count": 1,
"self": 0.03759667700001046
},
"TrainerController.start_learning": {
"total": 747.9340658640001,
"count": 1,
"self": 0.9398047080094329,
"children": {
"TrainerController._reset_env": {
"total": 4.947456068000065,
"count": 1,
"self": 4.947456068000065
},
"TrainerController.advance": {
"total": 741.8183962319906,
"count": 26158,
"self": 0.4589585900006341,
"children": {
"env_step": {
"total": 741.35943764199,
"count": 26158,
"self": 538.6103066839851,
"children": {
"SubprocessEnvManager._take_step": {
"total": 202.3030676960002,
"count": 26158,
"self": 2.9853221410094193,
"children": {
"TorchPolicy.evaluate": {
"total": 199.31774555499078,
"count": 26158,
"self": 199.31774555499078
}
}
},
"workers": {
"total": 0.4460632620047136,
"count": 26158,
"self": 0.0,
"children": {
"worker_root": {
"total": 745.122833673013,
"count": 26158,
"is_parallel": true,
"self": 346.0372864380188,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019644089999246717,
"count": 1,
"is_parallel": true,
"self": 0.0005948389999730352,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013695699999516364,
"count": 10,
"is_parallel": true,
"self": 0.0013695699999516364
}
}
},
"UnityEnvironment.step": {
"total": 0.1140114080000103,
"count": 1,
"is_parallel": true,
"self": 0.0014057659999480165,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046770500000548054,
"count": 1,
"is_parallel": true,
"self": 0.00046770500000548054
},
"communicator.exchange": {
"total": 0.10714145200006442,
"count": 1,
"is_parallel": true,
"self": 0.10714145200006442
},
"steps_from_proto": {
"total": 0.00499648499999239,
"count": 1,
"is_parallel": true,
"self": 0.0022938299998713774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027026550001210126,
"count": 10,
"is_parallel": true,
"self": 0.0027026550001210126
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 399.08554723499424,
"count": 26157,
"is_parallel": true,
"self": 16.526778740034388,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.684901275973857,
"count": 26157,
"is_parallel": true,
"self": 8.684901275973857
},
"communicator.exchange": {
"total": 316.69753171800176,
"count": 26157,
"is_parallel": true,
"self": 316.69753171800176
},
"steps_from_proto": {
"total": 57.17633550098424,
"count": 26157,
"is_parallel": true,
"self": 10.907611133061323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 46.268724367922914,
"count": 261570,
"is_parallel": true,
"self": 46.268724367922914
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.560099996022473e-05,
"count": 1,
"self": 6.560099996022473e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 735.6635864170456,
"count": 735463,
"is_parallel": true,
"self": 16.862353326136144,
"children": {
"process_trajectory": {
"total": 409.34913869791,
"count": 735463,
"is_parallel": true,
"self": 406.7417334879102,
"children": {
"RLTrainer._checkpoint": {
"total": 2.607405209999797,
"count": 5,
"is_parallel": true,
"self": 2.607405209999797
}
}
},
"_update_policy": {
"total": 309.45209439299947,
"count": 130,
"is_parallel": true,
"self": 112.86148769100714,
"children": {
"TorchPPOOptimizer.update": {
"total": 196.59060670199233,
"count": 6627,
"is_parallel": true,
"self": 196.59060670199233
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22834325500002706,
"count": 1,
"self": 0.0018251750000217726,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22651808000000528,
"count": 1,
"self": 0.22651808000000528
}
}
}
}
}
}
}