recepdemrci's picture
First Push
bf81821 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9772793650627136,
"min": 0.9772793650627136,
"max": 2.8704493045806885,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9320.3134765625,
"min": 9320.3134765625,
"max": 29396.271484375,
"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": 11.597536087036133,
"min": 0.4146325886249542,
"max": 11.597536087036133,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2261.51953125,
"min": 80.438720703125,
"max": 2345.206787109375,
"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": 0.06929774588492114,
"min": 0.06020424941151777,
"max": 0.07576566227670649,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2771909835396846,
"min": 0.2408169976460711,
"max": 0.37882831138353246,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18439011224636845,
"min": 0.12241628983368476,
"max": 0.28270213078050055,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7375604489854738,
"min": 0.48966515933473903,
"max": 1.4135106539025029,
"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": 23.15909090909091,
"min": 3.3636363636363638,
"max": 23.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1019.0,
"min": 148.0,
"max": 1247.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.15909090909091,
"min": 3.3636363636363638,
"max": 23.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1019.0,
"min": 148.0,
"max": 1247.0,
"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": "1720973077",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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 --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720973551"
},
"total": 474.03422938200004,
"count": 1,
"self": 0.4283003729999564,
"children": {
"run_training.setup": {
"total": 0.06414636599993173,
"count": 1,
"self": 0.06414636599993173
},
"TrainerController.start_learning": {
"total": 473.54178264300015,
"count": 1,
"self": 0.6275966510032731,
"children": {
"TrainerController._reset_env": {
"total": 2.7948913080000466,
"count": 1,
"self": 2.7948913080000466
},
"TrainerController.advance": {
"total": 470.0158782939967,
"count": 18200,
"self": 0.2904670220048047,
"children": {
"env_step": {
"total": 469.7254112719919,
"count": 18200,
"self": 302.6741738860069,
"children": {
"SubprocessEnvManager._take_step": {
"total": 166.74142881099783,
"count": 18200,
"self": 1.531051509991812,
"children": {
"TorchPolicy.evaluate": {
"total": 165.21037730100602,
"count": 18200,
"self": 165.21037730100602
}
}
},
"workers": {
"total": 0.30980857498718706,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.3142247650097,
"count": 18200,
"is_parallel": true,
"self": 240.60685379100494,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005175866000058704,
"count": 1,
"is_parallel": true,
"self": 0.0035991259999264003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001576740000132304,
"count": 10,
"is_parallel": true,
"self": 0.001576740000132304
}
}
},
"UnityEnvironment.step": {
"total": 0.03735106400006316,
"count": 1,
"is_parallel": true,
"self": 0.0007469460001630068,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040074599996842153,
"count": 1,
"is_parallel": true,
"self": 0.00040074599996842153
},
"communicator.exchange": {
"total": 0.034117897999976776,
"count": 1,
"is_parallel": true,
"self": 0.034117897999976776
},
"steps_from_proto": {
"total": 0.0020854739999549565,
"count": 1,
"is_parallel": true,
"self": 0.0004147959997453654,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016706780002095911,
"count": 10,
"is_parallel": true,
"self": 0.0016706780002095911
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.7073709740048,
"count": 18199,
"is_parallel": true,
"self": 10.429531704028477,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.587710341989464,
"count": 18199,
"is_parallel": true,
"self": 5.587710341989464
},
"communicator.exchange": {
"total": 180.28615695498138,
"count": 18199,
"is_parallel": true,
"self": 180.28615695498138
},
"steps_from_proto": {
"total": 35.40397197300547,
"count": 18199,
"is_parallel": true,
"self": 6.828537493024555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.575434479980913,
"count": 181990,
"is_parallel": true,
"self": 28.575434479980913
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015032000010251068,
"count": 1,
"self": 0.00015032000010251068,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 464.0663416250237,
"count": 697913,
"is_parallel": true,
"self": 15.768290491013886,
"children": {
"process_trajectory": {
"total": 257.2564003850099,
"count": 697913,
"is_parallel": true,
"self": 256.3743964100099,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8820039749999751,
"count": 4,
"is_parallel": true,
"self": 0.8820039749999751
}
}
},
"_update_policy": {
"total": 191.04165074899993,
"count": 90,
"is_parallel": true,
"self": 59.00701883600402,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.0346319129959,
"count": 4587,
"is_parallel": true,
"self": 132.0346319129959
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10326607000001786,
"count": 1,
"self": 0.0009916210001392756,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10227444899987859,
"count": 1,
"self": 0.10227444899987859
}
}
}
}
}
}
}