emylrahim's picture
First training of SnowballTarget
5168400
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9264958500862122,
"min": 0.9264958500862122,
"max": 2.865490436553955,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8846.1826171875,
"min": 8846.1826171875,
"max": 29345.48828125,
"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": 12.56182861328125,
"min": 0.29297131299972534,
"max": 12.56182861328125,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2449.556640625,
"min": 56.8364372253418,
"max": 2552.8701171875,
"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": 0.06045991228822066,
"min": 0.06045991228822066,
"max": 0.07845168523200817,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24183964915288264,
"min": 0.24183964915288264,
"max": 0.3507698182619803,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22616113649279465,
"min": 0.13087915316196708,
"max": 0.2855491095459929,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9046445459711786,
"min": 0.5235166126478683,
"max": 1.3238085432379854,
"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": 24.454545454545453,
"min": 3.4545454545454546,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1076.0,
"min": 152.0,
"max": 1360.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.454545454545453,
"min": 3.4545454545454546,
"max": 24.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1076.0,
"min": 152.0,
"max": 1360.0,
"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": "1677995601",
"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": "1.22.4",
"end_time_seconds": "1677996065"
},
"total": 464.7517819139998,
"count": 1,
"self": 0.4230025220003881,
"children": {
"run_training.setup": {
"total": 0.11721410699965418,
"count": 1,
"self": 0.11721410699965418
},
"TrainerController.start_learning": {
"total": 464.2115652849998,
"count": 1,
"self": 0.578986964989781,
"children": {
"TrainerController._reset_env": {
"total": 7.048426681999899,
"count": 1,
"self": 7.048426681999899
},
"TrainerController.advance": {
"total": 456.46493130300996,
"count": 18204,
"self": 0.2878462230437435,
"children": {
"env_step": {
"total": 456.1770850799662,
"count": 18204,
"self": 314.48137080293554,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.42722096098169,
"count": 18204,
"self": 1.656184612992547,
"children": {
"TorchPolicy.evaluate": {
"total": 139.77103634798914,
"count": 18204,
"self": 31.964393868012394,
"children": {
"TorchPolicy.sample_actions": {
"total": 107.80664247997674,
"count": 18204,
"self": 107.80664247997674
}
}
}
}
},
"workers": {
"total": 0.2684933160489891,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 462.6747564499801,
"count": 18204,
"is_parallel": true,
"self": 221.41252394299318,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002203992999966431,
"count": 1,
"is_parallel": true,
"self": 0.0007070170004226384,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014969759995437926,
"count": 10,
"is_parallel": true,
"self": 0.0014969759995437926
}
}
},
"UnityEnvironment.step": {
"total": 0.07408219700027985,
"count": 1,
"is_parallel": true,
"self": 0.0005631340009131236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003633189999163733,
"count": 1,
"is_parallel": true,
"self": 0.0003633189999163733
},
"communicator.exchange": {
"total": 0.06633769599966399,
"count": 1,
"is_parallel": true,
"self": 0.06633769599966399
},
"steps_from_proto": {
"total": 0.0068180479997863586,
"count": 1,
"is_parallel": true,
"self": 0.00046294399953694665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006355104000249412,
"count": 10,
"is_parallel": true,
"self": 0.006355104000249412
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.26223250698695,
"count": 18203,
"is_parallel": true,
"self": 9.520458856944515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.276184989013018,
"count": 18203,
"is_parallel": true,
"self": 5.276184989013018
},
"communicator.exchange": {
"total": 194.26299118201723,
"count": 18203,
"is_parallel": true,
"self": 194.26299118201723
},
"steps_from_proto": {
"total": 32.202597479012184,
"count": 18203,
"is_parallel": true,
"self": 6.871244465186464,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.33135301382572,
"count": 182030,
"is_parallel": true,
"self": 25.33135301382572
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013211900022724876,
"count": 1,
"self": 0.00013211900022724876,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.9892188191202,
"count": 415012,
"is_parallel": true,
"self": 10.215596421376631,
"children": {
"process_trajectory": {
"total": 258.06547441774455,
"count": 415012,
"is_parallel": true,
"self": 257.28236587774427,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7831085400002848,
"count": 4,
"is_parallel": true,
"self": 0.7831085400002848
}
}
},
"_update_policy": {
"total": 184.708147979999,
"count": 90,
"is_parallel": true,
"self": 66.29450398401377,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.41364399598524,
"count": 4587,
"is_parallel": true,
"self": 118.41364399598524
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11908821599990915,
"count": 1,
"self": 0.0008949210000537278,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11819329499985542,
"count": 1,
"self": 0.11819329499985542
}
}
}
}
}
}
}