pastells's picture
First training of SnowballTarget
92c05e1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0268162488937378,
"min": 1.0252732038497925,
"max": 2.867332935333252,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9804.0419921875,
"min": 9804.0419921875,
"max": 29364.357421875,
"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": 12.240530014038086,
"min": 0.4378846287727356,
"max": 12.240530014038086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2386.9033203125,
"min": 84.94961547851562,
"max": 2460.95166015625,
"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": 0.07064408452595886,
"min": 0.06452863171725767,
"max": 0.07499269578843001,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2825763381038354,
"min": 0.26256372235080816,
"max": 0.3648243600658972,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1984683932626949,
"min": 0.13663528032153477,
"max": 0.28311694422188927,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7938735730507795,
"min": 0.5465411212861391,
"max": 1.4155847211094463,
"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": 24.136363636363637,
"min": 3.5,
"max": 24.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1062.0,
"min": 154.0,
"max": 1326.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.136363636363637,
"min": 3.5,
"max": 24.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1062.0,
"min": 154.0,
"max": 1326.0,
"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": "1680180073",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1680180540"
},
"total": 466.47334982100006,
"count": 1,
"self": 0.43303608800010807,
"children": {
"run_training.setup": {
"total": 0.10992211000007046,
"count": 1,
"self": 0.10992211000007046
},
"TrainerController.start_learning": {
"total": 465.9303916229999,
"count": 1,
"self": 0.5264678110008845,
"children": {
"TrainerController._reset_env": {
"total": 9.168108152999935,
"count": 1,
"self": 9.168108152999935
},
"TrainerController.advance": {
"total": 456.1060138759991,
"count": 18201,
"self": 0.25628378999351753,
"children": {
"env_step": {
"total": 455.8497300860056,
"count": 18201,
"self": 327.7341135739989,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.85034884899221,
"count": 18201,
"self": 2.6990114210138927,
"children": {
"TorchPolicy.evaluate": {
"total": 125.15133742797832,
"count": 18201,
"self": 125.15133742797832
}
}
},
"workers": {
"total": 0.2652676630144697,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 464.4634038579985,
"count": 18201,
"is_parallel": true,
"self": 222.87926628599598,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005438627999978962,
"count": 1,
"is_parallel": true,
"self": 0.003944372000319163,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014942559996597993,
"count": 10,
"is_parallel": true,
"self": 0.0014942559996597993
}
}
},
"UnityEnvironment.step": {
"total": 0.059141677999946296,
"count": 1,
"is_parallel": true,
"self": 0.0005535739999231737,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041059500006213057,
"count": 1,
"is_parallel": true,
"self": 0.00041059500006213057
},
"communicator.exchange": {
"total": 0.056294214999979886,
"count": 1,
"is_parallel": true,
"self": 0.056294214999979886
},
"steps_from_proto": {
"total": 0.001883293999981106,
"count": 1,
"is_parallel": true,
"self": 0.00040899099985836074,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014743030001227453,
"count": 10,
"is_parallel": true,
"self": 0.0014743030001227453
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.58413757200253,
"count": 18200,
"is_parallel": true,
"self": 9.474535966010308,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.410780819992397,
"count": 18200,
"is_parallel": true,
"self": 5.410780819992397
},
"communicator.exchange": {
"total": 194.53017730100441,
"count": 18200,
"is_parallel": true,
"self": 194.53017730100441
},
"steps_from_proto": {
"total": 32.168643484995414,
"count": 18200,
"is_parallel": true,
"self": 6.309968858998104,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.85867462599731,
"count": 182000,
"is_parallel": true,
"self": 25.85867462599731
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001300189999255963,
"count": 1,
"self": 0.0001300189999255963,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.7241753750019,
"count": 414011,
"is_parallel": true,
"self": 9.99927057392756,
"children": {
"process_trajectory": {
"total": 251.48830973907445,
"count": 414011,
"is_parallel": true,
"self": 250.75812036507466,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7301893739997922,
"count": 4,
"is_parallel": true,
"self": 0.7301893739997922
}
}
},
"_update_policy": {
"total": 191.23659506199988,
"count": 90,
"is_parallel": true,
"self": 73.05796122400136,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.17863383799852,
"count": 4587,
"is_parallel": true,
"self": 118.17863383799852
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12967176400002245,
"count": 1,
"self": 0.0008875050000369811,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12878425899998547,
"count": 1,
"self": 0.12878425899998547
}
}
}
}
}
}
}