Deflyer's picture
First Push
b850e7d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9980511665344238,
"min": 0.9928345680236816,
"max": 2.860311985015869,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9485.478515625,
"min": 9485.478515625,
"max": 29198.064453125,
"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": 13.30695629119873,
"min": 0.4560312032699585,
"max": 13.30695629119873,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2594.8564453125,
"min": 88.47005462646484,
"max": 2699.0068359375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07131051168294911,
"min": 0.06249219415506505,
"max": 0.07131051168294911,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28524204673179643,
"min": 0.25575181505112543,
"max": 0.35109982917107546,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1725232808795922,
"min": 0.13809304306821157,
"max": 0.27122929727329925,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6900931235183688,
"min": 0.5523721722728463,
"max": 1.3561464863664963,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0776097306000009e-05,
"min": 1.0776097306000009e-05,
"max": 0.000389176002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.3104389224000035e-05,
"min": 4.3104389224000035e-05,
"max": 0.0018468800382800002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10134700000000002,
"min": 0.10134700000000002,
"max": 0.148647,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4053880000000001,
"min": 0.4053880000000001,
"max": 0.7308600000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828000000003,
"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": 26.227272727272727,
"min": 3.9318181818181817,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1154.0,
"min": 173.0,
"max": 1434.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.227272727272727,
"min": 3.9318181818181817,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1154.0,
"min": 173.0,
"max": 1434.0,
"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": "1742655703",
"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": "1742656177"
},
"total": 473.99708933900007,
"count": 1,
"self": 0.4394339749999858,
"children": {
"run_training.setup": {
"total": 0.023026036000032946,
"count": 1,
"self": 0.023026036000032946
},
"TrainerController.start_learning": {
"total": 473.53462932800005,
"count": 1,
"self": 0.3296984730021677,
"children": {
"TrainerController._reset_env": {
"total": 2.93644046899999,
"count": 1,
"self": 2.93644046899999
},
"TrainerController.advance": {
"total": 470.16960827199784,
"count": 18192,
"self": 0.3726100740007041,
"children": {
"env_step": {
"total": 310.30618800400134,
"count": 18192,
"self": 236.44137240899664,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.65243042000253,
"count": 18192,
"self": 1.3037376250034072,
"children": {
"TorchPolicy.evaluate": {
"total": 72.34869279499912,
"count": 18192,
"self": 72.34869279499912
}
}
},
"workers": {
"total": 0.21238517500216858,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.1420314019951,
"count": 18192,
"is_parallel": true,
"self": 264.3995200279933,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005446177999999691,
"count": 1,
"is_parallel": true,
"self": 0.0036657269999409436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001780451000058747,
"count": 10,
"is_parallel": true,
"self": 0.001780451000058747
}
}
},
"UnityEnvironment.step": {
"total": 0.04858224100001962,
"count": 1,
"is_parallel": true,
"self": 0.0005974709999918559,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004080420000036611,
"count": 1,
"is_parallel": true,
"self": 0.0004080420000036611
},
"communicator.exchange": {
"total": 0.044517127000005985,
"count": 1,
"is_parallel": true,
"self": 0.044517127000005985
},
"steps_from_proto": {
"total": 0.0030596010000181195,
"count": 1,
"is_parallel": true,
"self": 0.00036265300002469303,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026969479999934265,
"count": 10,
"is_parallel": true,
"self": 0.0026969479999934265
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 207.74251137400182,
"count": 18191,
"is_parallel": true,
"self": 10.114751243999933,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.595452403003776,
"count": 18191,
"is_parallel": true,
"self": 5.595452403003776
},
"communicator.exchange": {
"total": 159.0190835189968,
"count": 18191,
"is_parallel": true,
"self": 159.0190835189968
},
"steps_from_proto": {
"total": 33.013224208001304,
"count": 18191,
"is_parallel": true,
"self": 5.920949993018894,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.09227421498241,
"count": 181910,
"is_parallel": true,
"self": 27.09227421498241
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 159.4908101939958,
"count": 18192,
"self": 0.4410853809964692,
"children": {
"process_trajectory": {
"total": 28.571234342999787,
"count": 18192,
"self": 28.12471811699976,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4465162260000284,
"count": 4,
"self": 0.4465162260000284
}
}
},
"_update_policy": {
"total": 130.47849046999954,
"count": 90,
"self": 52.57611825000288,
"children": {
"TorchPPOOptimizer.update": {
"total": 77.90237221999666,
"count": 6116,
"self": 77.90237221999666
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1360000371496426e-06,
"count": 1,
"self": 1.1360000371496426e-06
},
"TrainerController._save_models": {
"total": 0.09888097800001105,
"count": 1,
"self": 0.0010148250000838743,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09786615299992718,
"count": 1,
"self": 0.09786615299992718
}
}
}
}
}
}
}