heidragon3045's picture
First Training of Snowball Target
e88bdc1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9503751993179321,
"min": 0.9503751993179321,
"max": 2.8551828861236572,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9074.1826171875,
"min": 9074.1826171875,
"max": 29302.7421875,
"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": 12.68356990814209,
"min": 0.3669761121273041,
"max": 12.68356990814209,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2473.296142578125,
"min": 71.19336700439453,
"max": 2572.99267578125,
"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": 0.06503815440045596,
"min": 0.06318839546841393,
"max": 0.07447893794439961,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26015261760182384,
"min": 0.2527535818736557,
"max": 0.3723946897219981,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21203043560187018,
"min": 0.114025042649112,
"max": 0.29374737365573056,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8481217424074807,
"min": 0.456100170596448,
"max": 1.393707631265416,
"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": 25.272727272727273,
"min": 3.340909090909091,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 147.0,
"max": 1373.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.340909090909091,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 147.0,
"max": 1373.0,
"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": "1680853892",
"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": "1680854353"
},
"total": 460.304888028,
"count": 1,
"self": 0.385941364999951,
"children": {
"run_training.setup": {
"total": 0.21272149599997192,
"count": 1,
"self": 0.21272149599997192
},
"TrainerController.start_learning": {
"total": 459.70622516700007,
"count": 1,
"self": 0.5668304209954158,
"children": {
"TrainerController._reset_env": {
"total": 5.339690410000003,
"count": 1,
"self": 5.339690410000003
},
"TrainerController.advance": {
"total": 453.6651566660047,
"count": 18202,
"self": 0.28243928699606613,
"children": {
"env_step": {
"total": 453.3827173790086,
"count": 18202,
"self": 333.0364607310205,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.07681670298939,
"count": 18202,
"self": 1.6843823719930242,
"children": {
"TorchPolicy.evaluate": {
"total": 118.39243433099637,
"count": 18202,
"self": 118.39243433099637
}
}
},
"workers": {
"total": 0.26943994499873725,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.3368030719966,
"count": 18202,
"is_parallel": true,
"self": 212.42604228800184,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0075612090000163334,
"count": 1,
"is_parallel": true,
"self": 0.00450211199995465,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0030590970000616835,
"count": 10,
"is_parallel": true,
"self": 0.0030590970000616835
}
}
},
"UnityEnvironment.step": {
"total": 0.04007349500000146,
"count": 1,
"is_parallel": true,
"self": 0.000638938000008693,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037163399997552915,
"count": 1,
"is_parallel": true,
"self": 0.00037163399997552915
},
"communicator.exchange": {
"total": 0.03717839699999104,
"count": 1,
"is_parallel": true,
"self": 0.03717839699999104
},
"steps_from_proto": {
"total": 0.0018845260000261987,
"count": 1,
"is_parallel": true,
"self": 0.0003828009999438109,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015017250000823879,
"count": 10,
"is_parallel": true,
"self": 0.0015017250000823879
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.91076078399476,
"count": 18201,
"is_parallel": true,
"self": 10.090631223992546,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.328311392994067,
"count": 18201,
"is_parallel": true,
"self": 5.328311392994067
},
"communicator.exchange": {
"total": 199.12030998400735,
"count": 18201,
"is_parallel": true,
"self": 199.12030998400735
},
"steps_from_proto": {
"total": 31.3715081830008,
"count": 18201,
"is_parallel": true,
"self": 6.160698977008678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.21080920599212,
"count": 182010,
"is_parallel": true,
"self": 25.21080920599212
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013631800004532124,
"count": 1,
"self": 0.00013631800004532124,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.4653333709697,
"count": 399928,
"is_parallel": true,
"self": 9.640850792967797,
"children": {
"process_trajectory": {
"total": 245.6523245060016,
"count": 399928,
"is_parallel": true,
"self": 244.4384498780018,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2138746279998145,
"count": 4,
"is_parallel": true,
"self": 1.2138746279998145
}
}
},
"_update_policy": {
"total": 195.1721580720003,
"count": 90,
"is_parallel": true,
"self": 74.59203390999886,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.58012416200143,
"count": 4584,
"is_parallel": true,
"self": 120.58012416200143
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1344113519999155,
"count": 1,
"self": 0.0008909609998681844,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1335203910000473,
"count": 1,
"self": 0.1335203910000473
}
}
}
}
}
}
}