Segamboam's picture
First Push :D
bbe0c28
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9068813920021057,
"min": 0.9068813920021057,
"max": 2.860630989074707,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8658.9033203125,
"min": 8658.9033203125,
"max": 29295.72265625,
"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": 12.965442657470703,
"min": 0.23182138800621033,
"max": 13.104299545288086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2528.26123046875,
"min": 44.973350524902344,
"max": 2673.277099609375,
"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": 0.07429939863961373,
"min": 0.06174401512446054,
"max": 0.07446241387001731,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2971975945584549,
"min": 0.24697606049784215,
"max": 0.3648744250360109,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19976693253014605,
"min": 0.10168797528489913,
"max": 0.29073425472951403,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7990677301205842,
"min": 0.40675190113959653,
"max": 1.45367127364757,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.00029193000269,
"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": 0.19731,
"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": 0.004865769,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.0,
"min": 2.75,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 121.0,
"max": 1403.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 2.75,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 121.0,
"max": 1403.0,
"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": "1674052105",
"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": "1.21.6",
"end_time_seconds": "1674052524"
},
"total": 418.641262352,
"count": 1,
"self": 0.39067804499995873,
"children": {
"run_training.setup": {
"total": 0.10265721099995062,
"count": 1,
"self": 0.10265721099995062
},
"TrainerController.start_learning": {
"total": 418.1479270960001,
"count": 1,
"self": 0.4982150819942035,
"children": {
"TrainerController._reset_env": {
"total": 10.159201446999987,
"count": 1,
"self": 10.159201446999987
},
"TrainerController.advance": {
"total": 407.36416270300595,
"count": 18201,
"self": 0.2681759030072044,
"children": {
"env_step": {
"total": 407.09598679999874,
"count": 18201,
"self": 265.54007991500293,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.30390492299568,
"count": 18201,
"self": 1.3704159209904674,
"children": {
"TorchPolicy.evaluate": {
"total": 139.93348900200522,
"count": 18201,
"self": 30.915569890007532,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.01791911199768,
"count": 18201,
"self": 109.01791911199768
}
}
}
}
},
"workers": {
"total": 0.25200196200012215,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 416.9827692679946,
"count": 18201,
"is_parallel": true,
"self": 202.66757678498323,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0066102450000471435,
"count": 1,
"is_parallel": true,
"self": 0.004274239000096713,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00233600599995043,
"count": 10,
"is_parallel": true,
"self": 0.00233600599995043
}
}
},
"UnityEnvironment.step": {
"total": 0.043144471999994494,
"count": 1,
"is_parallel": true,
"self": 0.0004359240001576836,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031160599996837846,
"count": 1,
"is_parallel": true,
"self": 0.00031160599996837846
},
"communicator.exchange": {
"total": 0.04058355399990887,
"count": 1,
"is_parallel": true,
"self": 0.04058355399990887
},
"steps_from_proto": {
"total": 0.0018133879999595592,
"count": 1,
"is_parallel": true,
"self": 0.000436149999927693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013772380000318662,
"count": 10,
"is_parallel": true,
"self": 0.0013772380000318662
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.3151924830114,
"count": 18200,
"is_parallel": true,
"self": 8.177479801009667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.758879452997462,
"count": 18200,
"is_parallel": true,
"self": 4.758879452997462
},
"communicator.exchange": {
"total": 172.3378963710062,
"count": 18200,
"is_parallel": true,
"self": 172.3378963710062
},
"steps_from_proto": {
"total": 29.040936857998076,
"count": 18200,
"is_parallel": true,
"self": 6.094292732978829,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.946644125019247,
"count": 182000,
"is_parallel": true,
"self": 22.946644125019247
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.4961999947190634e-05,
"count": 1,
"self": 4.4961999947190634e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 404.4711068469875,
"count": 334615,
"is_parallel": true,
"self": 8.809227948944795,
"children": {
"process_trajectory": {
"total": 232.80487663004283,
"count": 334615,
"is_parallel": true,
"self": 232.06150599904277,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7433706310000616,
"count": 4,
"is_parallel": true,
"self": 0.7433706310000616
}
}
},
"_update_policy": {
"total": 162.85700226799986,
"count": 90,
"is_parallel": true,
"self": 40.02330616700044,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.83369610099942,
"count": 4587,
"is_parallel": true,
"self": 122.83369610099942
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12630290200002037,
"count": 1,
"self": 0.0009007720000226982,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12540212999999767,
"count": 1,
"self": 0.12540212999999767
}
}
}
}
}
}
}