bhadresh-savani's picture
First Push
9c5349f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0631598234176636,
"min": 1.0631598234176636,
"max": 2.8709969520568848,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10151.0498046875,
"min": 10151.0498046875,
"max": 29401.880859375,
"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": 12.822891235351562,
"min": 0.42684927582740784,
"max": 12.876022338867188,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2500.4638671875,
"min": 82.80876159667969,
"max": 2626.70849609375,
"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": 0.06567090480501635,
"min": 0.06018087784745077,
"max": 0.07538790356267391,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2626836192200654,
"min": 0.24072351138980308,
"max": 0.37693951781336954,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20683194558117904,
"min": 0.12177519831012057,
"max": 0.28780473120072314,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8273277823247162,
"min": 0.4871007932404823,
"max": 1.4390236560036156,
"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": 24.863636363636363,
"min": 3.340909090909091,
"max": 25.4,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1094.0,
"min": 147.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.863636363636363,
"min": 3.340909090909091,
"max": 25.4,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1094.0,
"min": 147.0,
"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": "1682754991",
"python_version": "3.8.16 (default, Mar 2 2023, 03:21:46) \n[GCC 11.2.0]",
"command_line_arguments": "/root/miniconda3/envs/mlagent_env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu111",
"numpy_version": "1.21.2",
"end_time_seconds": "1682755301"
},
"total": 310.5018905121833,
"count": 1,
"self": 0.33202024176716805,
"children": {
"run_training.setup": {
"total": 0.01855240110307932,
"count": 1,
"self": 0.01855240110307932
},
"TrainerController.start_learning": {
"total": 310.15131786931306,
"count": 1,
"self": 0.5232408763840795,
"children": {
"TrainerController._reset_env": {
"total": 3.862336748279631,
"count": 1,
"self": 3.862336748279631
},
"TrainerController.advance": {
"total": 305.6691982327029,
"count": 18201,
"self": 0.24695426225662231,
"children": {
"env_step": {
"total": 305.4222439704463,
"count": 18201,
"self": 210.29368815664202,
"children": {
"SubprocessEnvManager._take_step": {
"total": 94.89324712473899,
"count": 18201,
"self": 1.4182725846767426,
"children": {
"TorchPolicy.evaluate": {
"total": 93.47497454006225,
"count": 18201,
"self": 93.47497454006225
}
}
},
"workers": {
"total": 0.23530868906527758,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 309.3728352850303,
"count": 18201,
"is_parallel": true,
"self": 147.19378593191504,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016991794109344482,
"count": 1,
"is_parallel": true,
"self": 0.0005290573462843895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011701220646500587,
"count": 10,
"is_parallel": true,
"self": 0.0011701220646500587
}
}
},
"UnityEnvironment.step": {
"total": 0.02755358349531889,
"count": 1,
"is_parallel": true,
"self": 0.00034823082387447357,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002639107406139374,
"count": 1,
"is_parallel": true,
"self": 0.0002639107406139374
},
"communicator.exchange": {
"total": 0.025958326645195484,
"count": 1,
"is_parallel": true,
"self": 0.025958326645195484
},
"steps_from_proto": {
"total": 0.0009831152856349945,
"count": 1,
"is_parallel": true,
"self": 0.0002425163984298706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007405988872051239,
"count": 10,
"is_parallel": true,
"self": 0.0007405988872051239
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 162.17904935311526,
"count": 18200,
"is_parallel": true,
"self": 5.1828024592250586,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.7867074962705374,
"count": 18200,
"is_parallel": true,
"self": 2.7867074962705374
},
"communicator.exchange": {
"total": 138.73807814717293,
"count": 18200,
"is_parallel": true,
"self": 138.73807814717293
},
"steps_from_proto": {
"total": 15.471461250446737,
"count": 18200,
"is_parallel": true,
"self": 3.546169617213309,
"children": {
"_process_rank_one_or_two_observation": {
"total": 11.925291633233428,
"count": 182000,
"is_parallel": true,
"self": 11.925291633233428
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010639522224664688,
"count": 1,
"self": 0.00010639522224664688,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 303.99282195884734,
"count": 424823,
"is_parallel": true,
"self": 5.487866745330393,
"children": {
"process_trajectory": {
"total": 162.69292725622654,
"count": 424823,
"is_parallel": true,
"self": 162.21692257001996,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4760046862065792,
"count": 4,
"is_parallel": true,
"self": 0.4760046862065792
}
}
},
"_update_policy": {
"total": 135.8120279572904,
"count": 90,
"is_parallel": true,
"self": 33.712141459807754,
"children": {
"TorchPPOOptimizer.update": {
"total": 102.09988649748266,
"count": 4587,
"is_parallel": true,
"self": 102.09988649748266
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0964356167241931,
"count": 1,
"self": 0.004720130003988743,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09171548672020435,
"count": 1,
"self": 0.09171548672020435
}
}
}
}
}
}
}