Mykolyt's picture
First push
7390ad4
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8674877882003784,
"min": 0.8674877882003784,
"max": 2.8679392337799072,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8282.7734375,
"min": 8282.7734375,
"max": 29370.56640625,
"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": 12.862395286560059,
"min": 0.44202443957328796,
"max": 12.862395286560059,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.1669921875,
"min": 85.75273895263672,
"max": 2613.558837890625,
"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": 0.06699254146243737,
"min": 0.05847817124954685,
"max": 0.0748871300180041,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2679701658497495,
"min": 0.2641611309886417,
"max": 0.37261550421352896,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19155820302080873,
"min": 0.12468744028706616,
"max": 0.2699508937550526,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7662328120832349,
"min": 0.49874976114826464,
"max": 1.349754468775263,
"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": 25.386363636363637,
"min": 3.409090909090909,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 150.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.409090909090909,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 150.0,
"max": 1392.0,
"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": "1676561566",
"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": "1676562059"
},
"total": 492.85389774299995,
"count": 1,
"self": 0.39285363599992706,
"children": {
"run_training.setup": {
"total": 0.1801717580000286,
"count": 1,
"self": 0.1801717580000286
},
"TrainerController.start_learning": {
"total": 492.280872349,
"count": 1,
"self": 0.5606375169993498,
"children": {
"TrainerController._reset_env": {
"total": 10.263347791000001,
"count": 1,
"self": 10.263347791000001
},
"TrainerController.advance": {
"total": 481.32145019800055,
"count": 18202,
"self": 0.2948354940049285,
"children": {
"env_step": {
"total": 481.0266147039956,
"count": 18202,
"self": 331.77188980199367,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.96071206699617,
"count": 18202,
"self": 1.5694540789936582,
"children": {
"TorchPolicy.evaluate": {
"total": 147.3912579880025,
"count": 18202,
"self": 32.81039702600333,
"children": {
"TorchPolicy.sample_actions": {
"total": 114.58086096199918,
"count": 18202,
"self": 114.58086096199918
}
}
}
}
},
"workers": {
"total": 0.29401283500578757,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 490.50444296599585,
"count": 18202,
"is_parallel": true,
"self": 239.4364666539842,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010189765000063744,
"count": 1,
"is_parallel": true,
"self": 0.004396916000018791,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005792849000044953,
"count": 10,
"is_parallel": true,
"self": 0.005792849000044953
}
}
},
"UnityEnvironment.step": {
"total": 0.03498976599996695,
"count": 1,
"is_parallel": true,
"self": 0.00039824500004215224,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035734000005049893,
"count": 1,
"is_parallel": true,
"self": 0.00035734000005049893
},
"communicator.exchange": {
"total": 0.03218406399992091,
"count": 1,
"is_parallel": true,
"self": 0.03218406399992091
},
"steps_from_proto": {
"total": 0.0020501169999533886,
"count": 1,
"is_parallel": true,
"self": 0.00045210599989786715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015980110000555214,
"count": 10,
"is_parallel": true,
"self": 0.0015980110000555214
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.06797631201164,
"count": 18201,
"is_parallel": true,
"self": 10.121487201005152,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.557962333999626,
"count": 18201,
"is_parallel": true,
"self": 5.557962333999626
},
"communicator.exchange": {
"total": 200.81702974400162,
"count": 18201,
"is_parallel": true,
"self": 200.81702974400162
},
"steps_from_proto": {
"total": 34.571497033005244,
"count": 18201,
"is_parallel": true,
"self": 7.718994844022745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.8525021889825,
"count": 182010,
"is_parallel": true,
"self": 26.8525021889825
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012639600004149543,
"count": 1,
"self": 0.00012639600004149543,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 477.55130674901056,
"count": 425053,
"is_parallel": true,
"self": 11.162238868990812,
"children": {
"process_trajectory": {
"total": 270.9268500320193,
"count": 425053,
"is_parallel": true,
"self": 270.1450325380192,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7818174940000517,
"count": 4,
"is_parallel": true,
"self": 0.7818174940000517
}
}
},
"_update_policy": {
"total": 195.46221784800048,
"count": 90,
"is_parallel": true,
"self": 70.4387778130025,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.02344003499798,
"count": 4587,
"is_parallel": true,
"self": 125.02344003499798
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13531044700005168,
"count": 1,
"self": 0.0008724980000351934,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1344379490000165,
"count": 1,
"self": 0.1344379490000165
}
}
}
}
}
}
}