mchen-hf-2023's picture
First Push
b40a130
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0426379442214966,
"min": 1.0426379442214966,
"max": 2.847580909729004,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9989.513671875,
"min": 9989.513671875,
"max": 29193.3984375,
"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": 12.841251373291016,
"min": 0.4036980867385864,
"max": 12.841251373291016,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.0439453125,
"min": 78.31742858886719,
"max": 2585.177734375,
"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": 0.06074948235085435,
"min": 0.06074948235085435,
"max": 0.07563937465858864,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2429979294034174,
"min": 0.2429979294034174,
"max": 0.3754537386486453,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20559396470586458,
"min": 0.13399063968944236,
"max": 0.3031363555138894,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8223758588234583,
"min": 0.5359625587577694,
"max": 1.515681777569447,
"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": 25.136363636363637,
"min": 3.9318181818181817,
"max": 25.4,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 173.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.9318181818181817,
"max": 25.4,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 173.0,
"max": 1397.0,
"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": "1695997557",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1695998086"
},
"total": 529.6374550990001,
"count": 1,
"self": 0.48164806700015106,
"children": {
"run_training.setup": {
"total": 0.04706943299993327,
"count": 1,
"self": 0.04706943299993327
},
"TrainerController.start_learning": {
"total": 529.108737599,
"count": 1,
"self": 0.670872671008965,
"children": {
"TrainerController._reset_env": {
"total": 4.714369180999938,
"count": 1,
"self": 4.714369180999938
},
"TrainerController.advance": {
"total": 523.565631371991,
"count": 18204,
"self": 0.3434732689916018,
"children": {
"env_step": {
"total": 523.2221581029994,
"count": 18204,
"self": 381.4938686469709,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.39233892000243,
"count": 18204,
"self": 1.8829070770032104,
"children": {
"TorchPolicy.evaluate": {
"total": 139.50943184299922,
"count": 18204,
"self": 139.50943184299922
}
}
},
"workers": {
"total": 0.3359505360260755,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 527.1898896830103,
"count": 18204,
"is_parallel": true,
"self": 245.29097450799577,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005982239999866579,
"count": 1,
"is_parallel": true,
"self": 0.004332563999696504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001649676000170075,
"count": 10,
"is_parallel": true,
"self": 0.001649676000170075
}
}
},
"UnityEnvironment.step": {
"total": 0.06713817700006075,
"count": 1,
"is_parallel": true,
"self": 0.0007134049999422132,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004213930001242261,
"count": 1,
"is_parallel": true,
"self": 0.0004213930001242261
},
"communicator.exchange": {
"total": 0.0627074569999877,
"count": 1,
"is_parallel": true,
"self": 0.0627074569999877
},
"steps_from_proto": {
"total": 0.0032959220000066125,
"count": 1,
"is_parallel": true,
"self": 0.00038705399947502883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029088680005315837,
"count": 10,
"is_parallel": true,
"self": 0.0029088680005315837
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 281.8989151750145,
"count": 18203,
"is_parallel": true,
"self": 11.889678012029663,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.001269730995773,
"count": 18203,
"is_parallel": true,
"self": 6.001269730995773
},
"communicator.exchange": {
"total": 223.90429688399672,
"count": 18203,
"is_parallel": true,
"self": 223.90429688399672
},
"steps_from_proto": {
"total": 40.10367054799235,
"count": 18203,
"is_parallel": true,
"self": 7.641919977011412,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.46175057098094,
"count": 182030,
"is_parallel": true,
"self": 32.46175057098094
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001499850000072911,
"count": 1,
"self": 0.0001499850000072911,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 519.2404951709814,
"count": 504637,
"is_parallel": true,
"self": 12.352541427868118,
"children": {
"process_trajectory": {
"total": 285.1025441271122,
"count": 504637,
"is_parallel": true,
"self": 283.7610243381123,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3415197889999035,
"count": 4,
"is_parallel": true,
"self": 1.3415197889999035
}
}
},
"_update_policy": {
"total": 221.78540961600106,
"count": 90,
"is_parallel": true,
"self": 85.69566093599178,
"children": {
"TorchPPOOptimizer.update": {
"total": 136.08974868000928,
"count": 4584,
"is_parallel": true,
"self": 136.08974868000928
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15771439000013743,
"count": 1,
"self": 0.0008951470001647976,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15681924299997263,
"count": 1,
"self": 0.15681924299997263
}
}
}
}
}
}
}