andrei-saceleanu's picture
First SnowballTarget model
d94e276
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.836129903793335,
"min": 0.836129903793335,
"max": 2.8605763912200928,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7983.3681640625,
"min": 7983.3681640625,
"max": 29263.6953125,
"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": 12.98047161102295,
"min": 0.4243259131908417,
"max": 12.98047161102295,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.19189453125,
"min": 82.31922912597656,
"max": 2642.918212890625,
"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": 0.07347743756590895,
"min": 0.06466688621531277,
"max": 0.07888417892805306,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2939097502636358,
"min": 0.2586675448612511,
"max": 0.3944208946402653,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19028332800257441,
"min": 0.13397137213420746,
"max": 0.2798478311183406,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7611333120102977,
"min": 0.5358854885368298,
"max": 1.399239155591703,
"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": 25.795454545454547,
"min": 3.840909090909091,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1135.0,
"min": 169.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.795454545454547,
"min": 3.840909090909091,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1135.0,
"min": 169.0,
"max": 1410.0,
"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": "1673422137",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673422572"
},
"total": 435.0461647379999,
"count": 1,
"self": 0.3861834379999891,
"children": {
"run_training.setup": {
"total": 0.11783204400001068,
"count": 1,
"self": 0.11783204400001068
},
"TrainerController.start_learning": {
"total": 434.5421492559999,
"count": 1,
"self": 0.5431838040110506,
"children": {
"TrainerController._reset_env": {
"total": 7.305497779000007,
"count": 1,
"self": 7.305497779000007
},
"TrainerController.advance": {
"total": 426.5747223449887,
"count": 18202,
"self": 0.29595713798835277,
"children": {
"env_step": {
"total": 426.27876520700033,
"count": 18202,
"self": 281.0426490060089,
"children": {
"SubprocessEnvManager._take_step": {
"total": 144.95410001999733,
"count": 18202,
"self": 1.4197632469863493,
"children": {
"TorchPolicy.evaluate": {
"total": 143.53433677301098,
"count": 18202,
"self": 32.77830804901578,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.7560287239952,
"count": 18202,
"self": 110.7560287239952
}
}
}
}
},
"workers": {
"total": 0.2820161809941055,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.3209102590022,
"count": 18202,
"is_parallel": true,
"self": 208.23148781601117,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006484484999987217,
"count": 1,
"is_parallel": true,
"self": 0.0037046850001161147,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002779799999871102,
"count": 10,
"is_parallel": true,
"self": 0.002779799999871102
}
}
},
"UnityEnvironment.step": {
"total": 0.030419146999975055,
"count": 1,
"is_parallel": true,
"self": 0.00041667100003905944,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003536079999548747,
"count": 1,
"is_parallel": true,
"self": 0.0003536079999548747
},
"communicator.exchange": {
"total": 0.028272056999981032,
"count": 1,
"is_parallel": true,
"self": 0.028272056999981032
},
"steps_from_proto": {
"total": 0.0013768110000000888,
"count": 1,
"is_parallel": true,
"self": 0.0003419370000301569,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001034873999969932,
"count": 10,
"is_parallel": true,
"self": 0.001034873999969932
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.089422442991,
"count": 18201,
"is_parallel": true,
"self": 8.580182258987065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.08783514099855,
"count": 18201,
"is_parallel": true,
"self": 5.08783514099855
},
"communicator.exchange": {
"total": 180.829661985994,
"count": 18201,
"is_parallel": true,
"self": 180.829661985994
},
"steps_from_proto": {
"total": 30.5917430570114,
"count": 18201,
"is_parallel": true,
"self": 6.608391515023641,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.98335154198776,
"count": 182010,
"is_parallel": true,
"self": 23.98335154198776
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.527400005827076e-05,
"count": 1,
"self": 4.527400005827076e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 423.49884430894554,
"count": 352936,
"is_parallel": true,
"self": 8.833773916954328,
"children": {
"process_trajectory": {
"total": 241.700655902991,
"count": 352936,
"is_parallel": true,
"self": 240.3818133209909,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3188425820001157,
"count": 4,
"is_parallel": true,
"self": 1.3188425820001157
}
}
},
"_update_policy": {
"total": 172.9644144890002,
"count": 90,
"is_parallel": true,
"self": 45.94995281799868,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.01446167100153,
"count": 4587,
"is_parallel": true,
"self": 127.01446167100153
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11870005400010086,
"count": 1,
"self": 0.0009213910002472403,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11777866299985362,
"count": 1,
"self": 0.11777866299985362
}
}
}
}
}
}
}