faelwen's picture
First Push
89ff9ae verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.3305416107177734,
"min": 2.3305416107177734,
"max": 2.835263252258301,
"count": 5
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 23790.16796875,
"min": 23790.16796875,
"max": 28942.3671875,
"count": 5
},
"SnowballTarget.Step.mean": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Step.sum": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 4.754555702209473,
"min": 0.43670034408569336,
"max": 4.754555702209473,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 922.3837890625,
"min": 84.71986389160156,
"max": 922.3837890625,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06749012482103746,
"min": 0.06360095050414183,
"max": 0.07430527215886767,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26996049928414984,
"min": 0.26996049928414984,
"max": 0.3679471365178282,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.29531476792751576,
"min": 0.11602258269547247,
"max": 0.29531476792751576,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.181259071710063,
"min": 0.4640903307818899,
"max": 1.3081267183902217,
"count": 5
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.9928090024000003e-05,
"min": 2.9928090024000003e-05,
"max": 0.00026752801082399996,
"count": 5
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00011971236009600001,
"min": 0.00011971236009600001,
"max": 0.0010701120432959998,
"count": 5
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10997600000000002,
"min": 0.10997600000000002,
"max": 0.18917599999999998,
"count": 5
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4399040000000001,
"min": 0.4399040000000001,
"max": 0.8468800000000001,
"count": 5
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0005078024,
"min": 0.0005078024,
"max": 0.0044598824,
"count": 5
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0020312096,
"min": 0.0020312096,
"max": 0.0178395296,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 11.636363636363637,
"min": 3.522727272727273,
"max": 11.636363636363637,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 512.0,
"min": 155.0,
"max": 574.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 11.636363636363637,
"min": 3.522727272727273,
"max": 11.636363636363637,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 512.0,
"min": 155.0,
"max": 574.0,
"count": 5
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1741165197",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741165315"
},
"total": 117.87080796599992,
"count": 1,
"self": 0.4836452439998311,
"children": {
"run_training.setup": {
"total": 0.030565987000045425,
"count": 1,
"self": 0.030565987000045425
},
"TrainerController.start_learning": {
"total": 117.35659673500004,
"count": 1,
"self": 0.10830407799835484,
"children": {
"TrainerController._reset_env": {
"total": 3.641313077999939,
"count": 1,
"self": 3.641313077999939
},
"TrainerController.advance": {
"total": 113.51403512100171,
"count": 4592,
"self": 0.11018208000803043,
"children": {
"env_step": {
"total": 81.71087083999828,
"count": 4592,
"self": 62.60961218300281,
"children": {
"SubprocessEnvManager._take_step": {
"total": 19.03723103400182,
"count": 4592,
"self": 0.35280486200076666,
"children": {
"TorchPolicy.evaluate": {
"total": 18.684426172001054,
"count": 4592,
"self": 18.684426172001054
}
}
},
"workers": {
"total": 0.06402762299364895,
"count": 4592,
"self": 0.0,
"children": {
"worker_root": {
"total": 116.61878438799738,
"count": 4592,
"is_parallel": true,
"self": 61.88920641999732,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007250397999996494,
"count": 1,
"is_parallel": true,
"self": 0.0051886010000998795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020617969998966146,
"count": 10,
"is_parallel": true,
"self": 0.0020617969998966146
}
}
},
"UnityEnvironment.step": {
"total": 0.03756583100005173,
"count": 1,
"is_parallel": true,
"self": 0.0006264939999027774,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004127090001020406,
"count": 1,
"is_parallel": true,
"self": 0.0004127090001020406
},
"communicator.exchange": {
"total": 0.03456737999999859,
"count": 1,
"is_parallel": true,
"self": 0.03456737999999859
},
"steps_from_proto": {
"total": 0.0019592480000483192,
"count": 1,
"is_parallel": true,
"self": 0.0004314120001254196,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015278359999228996,
"count": 10,
"is_parallel": true,
"self": 0.0015278359999228996
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 54.72957796800006,
"count": 4591,
"is_parallel": true,
"self": 2.557098470992514,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.3984140160030165,
"count": 4591,
"is_parallel": true,
"self": 1.3984140160030165
},
"communicator.exchange": {
"total": 42.53117029000248,
"count": 4591,
"is_parallel": true,
"self": 42.53117029000248
},
"steps_from_proto": {
"total": 8.242895191002049,
"count": 4591,
"is_parallel": true,
"self": 1.5145174139917117,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6.728377777010337,
"count": 45910,
"is_parallel": true,
"self": 6.728377777010337
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 31.692982200995402,
"count": 4592,
"self": 0.1365849479946064,
"children": {
"process_trajectory": {
"total": 7.23959677200105,
"count": 4592,
"self": 6.945374661000983,
"children": {
"RLTrainer._checkpoint": {
"total": 0.29422211100006734,
"count": 1,
"self": 0.29422211100006734
}
}
},
"_update_policy": {
"total": 24.316800480999746,
"count": 22,
"self": 9.907981758000687,
"children": {
"TorchPPOOptimizer.update": {
"total": 14.408818722999058,
"count": 1119,
"self": 14.408818722999058
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.079999472305644e-07,
"count": 1,
"self": 9.079999472305644e-07
},
"TrainerController._save_models": {
"total": 0.09294355000008636,
"count": 1,
"self": 0.0009711720000495916,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09197237800003677,
"count": 1,
"self": 0.09197237800003677
}
}
}
}
}
}
}