alekom's picture
First Push
bd065c7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9257011413574219,
"min": 0.9228804111480713,
"max": 2.8633644580841064,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8879.3251953125,
"min": 8879.3251953125,
"max": 29323.71484375,
"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": 12.982211112976074,
"min": 0.38885992765426636,
"max": 12.982211112976074,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.53125,
"min": 75.43882751464844,
"max": 2642.98388671875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06560597350928184,
"min": 0.06336435609880615,
"max": 0.07607767740081922,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26242389403712735,
"min": 0.26242389403712735,
"max": 0.37212905801339624,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19866122078954004,
"min": 0.12306531696516436,
"max": 0.29010567203456283,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7946448831581602,
"min": 0.49226126786065744,
"max": 1.450528360172814,
"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": 3.2954545454545454,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 145.0,
"max": 1383.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.2954545454545454,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 145.0,
"max": 1383.0,
"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": "1711622329",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711622802"
},
"total": 473.24241558999984,
"count": 1,
"self": 0.6406450219997168,
"children": {
"run_training.setup": {
"total": 0.08019494500013025,
"count": 1,
"self": 0.08019494500013025
},
"TrainerController.start_learning": {
"total": 472.521575623,
"count": 1,
"self": 0.6402244100027019,
"children": {
"TrainerController._reset_env": {
"total": 3.3938460259996646,
"count": 1,
"self": 3.3938460259996646
},
"TrainerController.advance": {
"total": 468.3456285989978,
"count": 18209,
"self": 0.2974203979865706,
"children": {
"env_step": {
"total": 468.0482082010112,
"count": 18209,
"self": 305.59839538401184,
"children": {
"SubprocessEnvManager._take_step": {
"total": 162.1250430590162,
"count": 18209,
"self": 1.573527308019493,
"children": {
"TorchPolicy.evaluate": {
"total": 160.5515157509967,
"count": 18209,
"self": 160.5515157509967
}
}
},
"workers": {
"total": 0.32476975798317653,
"count": 18209,
"self": 0.0,
"children": {
"worker_root": {
"total": 471.23208399200166,
"count": 18209,
"is_parallel": true,
"self": 231.48071599398327,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0070074990003377025,
"count": 1,
"is_parallel": true,
"self": 0.004757967999921675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022495310004160274,
"count": 10,
"is_parallel": true,
"self": 0.0022495310004160274
}
}
},
"UnityEnvironment.step": {
"total": 0.03733373099976234,
"count": 1,
"is_parallel": true,
"self": 0.0007045040001685265,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043294399984006304,
"count": 1,
"is_parallel": true,
"self": 0.00043294399984006304
},
"communicator.exchange": {
"total": 0.03408686900002067,
"count": 1,
"is_parallel": true,
"self": 0.03408686900002067
},
"steps_from_proto": {
"total": 0.0021094139997330785,
"count": 1,
"is_parallel": true,
"self": 0.0004517859997577034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016576279999753751,
"count": 10,
"is_parallel": true,
"self": 0.0016576279999753751
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.7513679980184,
"count": 18208,
"is_parallel": true,
"self": 10.973929328003578,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.666455219024556,
"count": 18208,
"is_parallel": true,
"self": 5.666455219024556
},
"communicator.exchange": {
"total": 187.66767079100782,
"count": 18208,
"is_parallel": true,
"self": 187.66767079100782
},
"steps_from_proto": {
"total": 35.44331265998244,
"count": 18208,
"is_parallel": true,
"self": 6.847370658141244,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.595942001841195,
"count": 182080,
"is_parallel": true,
"self": 28.595942001841195
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016435299994554953,
"count": 1,
"self": 0.00016435299994554953,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.585189676799,
"count": 721534,
"is_parallel": true,
"self": 15.541325840846639,
"children": {
"process_trajectory": {
"total": 256.0858572919519,
"count": 721534,
"is_parallel": true,
"self": 255.2716337269526,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8142235649993381,
"count": 4,
"is_parallel": true,
"self": 0.8142235649993381
}
}
},
"_update_policy": {
"total": 190.95800654400045,
"count": 90,
"is_parallel": true,
"self": 53.92424817100209,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.03375837299836,
"count": 4587,
"is_parallel": true,
"self": 137.03375837299836
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14171223499988628,
"count": 1,
"self": 0.0014120820001153334,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14030015299977094,
"count": 1,
"self": 0.14030015299977094
}
}
}
}
}
}
}