SleepyM's picture
First Push
afcefb0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9775113463401794,
"min": 0.961328387260437,
"max": 2.8612008094787598,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9290.267578125,
"min": 9290.267578125,
"max": 29207.138671875,
"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": 12.140725135803223,
"min": 0.5178783535957336,
"max": 12.140725135803223,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2367.44140625,
"min": 100.46839904785156,
"max": 2455.75927734375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06661416197654461,
"min": 0.06294432543874398,
"max": 0.0750073496448892,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26645664790617846,
"min": 0.257997463347719,
"max": 0.37390745571225553,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23273173799993946,
"min": 0.13299801412915044,
"max": 0.311716830905746,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9309269519997578,
"min": 0.5319920565166018,
"max": 1.55858415452873,
"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.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.Environment.CumulativeReward.mean": {
"value": 23.886363636363637,
"min": 3.7954545454545454,
"max": 24.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1051.0,
"min": 167.0,
"max": 1290.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.886363636363637,
"min": 3.7954545454545454,
"max": 24.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1051.0,
"min": 167.0,
"max": 1290.0,
"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": "1748954674",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748955096"
},
"total": 422.339564183,
"count": 1,
"self": 0.6988841490000368,
"children": {
"run_training.setup": {
"total": 0.024084558999902583,
"count": 1,
"self": 0.024084558999902583
},
"TrainerController.start_learning": {
"total": 421.61659547500005,
"count": 1,
"self": 0.33852680297309234,
"children": {
"TrainerController._reset_env": {
"total": 3.8928069279999136,
"count": 1,
"self": 3.8928069279999136
},
"TrainerController.advance": {
"total": 417.2579956540271,
"count": 18192,
"self": 0.3790865700248105,
"children": {
"env_step": {
"total": 295.6133644,
"count": 18192,
"self": 226.3657765209881,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.04565532901518,
"count": 18192,
"self": 1.2455409200126724,
"children": {
"TorchPolicy.evaluate": {
"total": 67.8001144090025,
"count": 18192,
"self": 67.8001144090025
}
}
},
"workers": {
"total": 0.20193254999674082,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 420.0980354829936,
"count": 18192,
"is_parallel": true,
"self": 221.4671462949916,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005904454000074111,
"count": 1,
"is_parallel": true,
"self": 0.004343948000268938,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001560505999805173,
"count": 10,
"is_parallel": true,
"self": 0.001560505999805173
}
}
},
"UnityEnvironment.step": {
"total": 0.0357991390000052,
"count": 1,
"is_parallel": true,
"self": 0.0005886009998903319,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039075100005447894,
"count": 1,
"is_parallel": true,
"self": 0.00039075100005447894
},
"communicator.exchange": {
"total": 0.03302851000000828,
"count": 1,
"is_parallel": true,
"self": 0.03302851000000828
},
"steps_from_proto": {
"total": 0.001791277000052105,
"count": 1,
"is_parallel": true,
"self": 0.0003615950002995305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014296819997525745,
"count": 10,
"is_parallel": true,
"self": 0.0014296819997525745
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 198.63088918800202,
"count": 18191,
"is_parallel": true,
"self": 9.648503116997631,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.454576768992865,
"count": 18191,
"is_parallel": true,
"self": 5.454576768992865
},
"communicator.exchange": {
"total": 152.63609046201054,
"count": 18191,
"is_parallel": true,
"self": 152.63609046201054
},
"steps_from_proto": {
"total": 30.891718840000976,
"count": 18191,
"is_parallel": true,
"self": 5.497862369973973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.393856470027004,
"count": 181910,
"is_parallel": true,
"self": 25.393856470027004
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.2655446840023,
"count": 18192,
"self": 0.4236595640076075,
"children": {
"process_trajectory": {
"total": 27.01809445699564,
"count": 18192,
"self": 26.53265814699546,
"children": {
"RLTrainer._checkpoint": {
"total": 0.48543631000018195,
"count": 4,
"self": 0.48543631000018195
}
}
},
"_update_policy": {
"total": 93.82379066299904,
"count": 90,
"self": 37.89869857200665,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.92509209099239,
"count": 4587,
"self": 55.92509209099239
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1709998943842947e-06,
"count": 1,
"self": 1.1709998943842947e-06
},
"TrainerController._save_models": {
"total": 0.12726491900002657,
"count": 1,
"self": 0.0011481300000468764,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1261167889999797,
"count": 1,
"self": 0.1261167889999797
}
}
}
}
}
}
}