roapple10's picture
First Push
bc49373
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8800144791603088,
"min": 0.8713040947914124,
"max": 2.850278615951538,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8412.05859375,
"min": 8412.05859375,
"max": 29189.703125,
"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": 12.91809368133545,
"min": 0.4597223699092865,
"max": 12.91809368133545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2519.0283203125,
"min": 89.18614196777344,
"max": 2623.283203125,
"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": 0.06445874988179746,
"min": 0.06317451335501163,
"max": 0.07264116962874587,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25783499952718986,
"min": 0.2569833219019404,
"max": 0.3632058481437293,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20427465643368514,
"min": 0.15516522225202517,
"max": 0.28659063085816266,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8170986257347406,
"min": 0.6206608890081007,
"max": 1.366180964252528,
"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": 25.318181818181817,
"min": 4.0,
"max": 25.509090909090908,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 176.0,
"max": 1403.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 4.0,
"max": 25.509090909090908,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 176.0,
"max": 1403.0,
"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": "1675757546",
"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": "1675758018"
},
"total": 471.75559363800005,
"count": 1,
"self": 0.3813210450001634,
"children": {
"run_training.setup": {
"total": 0.11135904899992966,
"count": 1,
"self": 0.11135904899992966
},
"TrainerController.start_learning": {
"total": 471.26291354399996,
"count": 1,
"self": 0.5590334129863095,
"children": {
"TrainerController._reset_env": {
"total": 9.278821080000057,
"count": 1,
"self": 9.278821080000057
},
"TrainerController.advance": {
"total": 461.3052957350136,
"count": 18204,
"self": 0.28589115200747983,
"children": {
"env_step": {
"total": 461.0194045830061,
"count": 18204,
"self": 314.5628287989832,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.1731717800103,
"count": 18204,
"self": 1.4783277750156003,
"children": {
"TorchPolicy.evaluate": {
"total": 144.6948440049947,
"count": 18204,
"self": 32.552857273993936,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.14198673100077,
"count": 18204,
"self": 112.14198673100077
}
}
}
}
},
"workers": {
"total": 0.2834040040125956,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 469.54667589398014,
"count": 18204,
"is_parallel": true,
"self": 226.32253869497492,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006947542000034446,
"count": 1,
"is_parallel": true,
"self": 0.0039262749999124935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003021267000121952,
"count": 10,
"is_parallel": true,
"self": 0.003021267000121952
}
}
},
"UnityEnvironment.step": {
"total": 0.049021639999978106,
"count": 1,
"is_parallel": true,
"self": 0.0005556950000027427,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002644580000605856,
"count": 1,
"is_parallel": true,
"self": 0.0002644580000605856
},
"communicator.exchange": {
"total": 0.046285983999950986,
"count": 1,
"is_parallel": true,
"self": 0.046285983999950986
},
"steps_from_proto": {
"total": 0.0019155029999637918,
"count": 1,
"is_parallel": true,
"self": 0.0004445739998573117,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00147092900010648,
"count": 10,
"is_parallel": true,
"self": 0.00147092900010648
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.2241371990052,
"count": 18203,
"is_parallel": true,
"self": 9.431659800031866,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.431039756995119,
"count": 18203,
"is_parallel": true,
"self": 5.431039756995119
},
"communicator.exchange": {
"total": 193.3304284510034,
"count": 18203,
"is_parallel": true,
"self": 193.3304284510034
},
"steps_from_proto": {
"total": 35.03100919097483,
"count": 18203,
"is_parallel": true,
"self": 7.317542391993015,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.713466798981813,
"count": 182030,
"is_parallel": true,
"self": 27.713466798981813
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001021339999169868,
"count": 1,
"self": 0.0001021339999169868,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 457.84515344799,
"count": 404438,
"is_parallel": true,
"self": 10.5695948038923,
"children": {
"process_trajectory": {
"total": 262.78688450209745,
"count": 404438,
"is_parallel": true,
"self": 261.8776654010974,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9092191010000761,
"count": 4,
"is_parallel": true,
"self": 0.9092191010000761
}
}
},
"_update_policy": {
"total": 184.48867414200026,
"count": 90,
"is_parallel": true,
"self": 64.07029393799758,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.41838020400269,
"count": 4587,
"is_parallel": true,
"self": 120.41838020400269
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11966118200007259,
"count": 1,
"self": 0.0008182430001397734,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11884293899993281,
"count": 1,
"self": 0.11884293899993281
}
}
}
}
}
}
}