ksanchis's picture
First Push
3d5a130
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9764401912689209,
"min": 0.945227324962616,
"max": 2.8615410327911377,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9323.05078125,
"min": 9323.05078125,
"max": 29367.99609375,
"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": 12.895182609558105,
"min": 0.2604747712612152,
"max": 12.895182609558105,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2514.560546875,
"min": 50.532108306884766,
"max": 2611.929443359375,
"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": 0.06968925698339601,
"min": 0.06088368512756264,
"max": 0.07512565732490746,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27875702793358403,
"min": 0.24353474051025056,
"max": 0.3756282866245373,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18915142644854155,
"min": 0.10427256538327236,
"max": 0.2738264622349365,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7566057057941662,
"min": 0.4170902615330894,
"max": 1.3342951875106963,
"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": 25.681818181818183,
"min": 3.1136363636363638,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 137.0,
"max": 1385.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 3.1136363636363638,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 137.0,
"max": 1385.0,
"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": "1699544504",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699544979"
},
"total": 475.23341463500003,
"count": 1,
"self": 0.4299926129999676,
"children": {
"run_training.setup": {
"total": 0.06582722200005264,
"count": 1,
"self": 0.06582722200005264
},
"TrainerController.start_learning": {
"total": 474.7375948,
"count": 1,
"self": 0.5560651389821487,
"children": {
"TrainerController._reset_env": {
"total": 8.111682223999992,
"count": 1,
"self": 8.111682223999992
},
"TrainerController.advance": {
"total": 465.9853487910177,
"count": 18199,
"self": 0.2754220140259349,
"children": {
"env_step": {
"total": 465.7099267769918,
"count": 18199,
"self": 316.3600094199859,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.97880084100234,
"count": 18199,
"self": 1.476750330002119,
"children": {
"TorchPolicy.evaluate": {
"total": 147.50205051100022,
"count": 18199,
"self": 147.50205051100022
}
}
},
"workers": {
"total": 0.37111651600355344,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 473.45521885499136,
"count": 18199,
"is_parallel": true,
"self": 232.90535067498172,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006313223000006474,
"count": 1,
"is_parallel": true,
"self": 0.004100234000134151,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002212988999872323,
"count": 10,
"is_parallel": true,
"self": 0.002212988999872323
}
}
},
"UnityEnvironment.step": {
"total": 0.03710775499996544,
"count": 1,
"is_parallel": true,
"self": 0.000563213000077667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036084499993194186,
"count": 1,
"is_parallel": true,
"self": 0.00036084499993194186
},
"communicator.exchange": {
"total": 0.03422928999998476,
"count": 1,
"is_parallel": true,
"self": 0.03422928999998476
},
"steps_from_proto": {
"total": 0.00195440699997107,
"count": 1,
"is_parallel": true,
"self": 0.00037082600022131373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015835809997497563,
"count": 10,
"is_parallel": true,
"self": 0.0015835809997497563
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.54986818000964,
"count": 18198,
"is_parallel": true,
"self": 10.746762383008445,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.627822511998602,
"count": 18198,
"is_parallel": true,
"self": 5.627822511998602
},
"communicator.exchange": {
"total": 188.73981469899547,
"count": 18198,
"is_parallel": true,
"self": 188.73981469899547
},
"steps_from_proto": {
"total": 35.43546858600712,
"count": 18198,
"is_parallel": true,
"self": 6.721741278026116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.713727307981003,
"count": 181980,
"is_parallel": true,
"self": 28.713727307981003
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010442100006002875,
"count": 1,
"self": 0.00010442100006002875,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.05765316401846,
"count": 483197,
"is_parallel": true,
"self": 10.498898235026218,
"children": {
"process_trajectory": {
"total": 261.9359072169917,
"count": 483197,
"is_parallel": true,
"self": 261.1056992099917,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8302080070000102,
"count": 4,
"is_parallel": true,
"self": 0.8302080070000102
}
}
},
"_update_policy": {
"total": 189.62284771200052,
"count": 90,
"is_parallel": true,
"self": 57.808879709002326,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.8139680029982,
"count": 4587,
"is_parallel": true,
"self": 131.8139680029982
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08439422500009641,
"count": 1,
"self": 0.0007679540001390706,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08362627099995734,
"count": 1,
"self": 0.08362627099995734
}
}
}
}
}
}
}