sigma-bit-dot's picture
First training of SnowballTarget
63edf40
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9986429214477539,
"min": 0.9986429214477539,
"max": 2.8558294773101807,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9524.0576171875,
"min": 9524.0576171875,
"max": 29372.20703125,
"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": 12.862688064575195,
"min": 0.4030326008796692,
"max": 12.862688064575195,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2508.22412109375,
"min": 78.18832397460938,
"max": 2617.999267578125,
"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": 0.07419336125638117,
"min": 0.06065334403275284,
"max": 0.07774886398589896,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29677344502552466,
"min": 0.24261337613101136,
"max": 0.3887443199294948,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20384712568392938,
"min": 0.11837265514038212,
"max": 0.2826430266394334,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8153885027357175,
"min": 0.47349062056152846,
"max": 1.4132151331971672,
"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": 25.204545454545453,
"min": 3.340909090909091,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 147.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.340909090909091,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 147.0,
"max": 1416.0,
"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": "1702629629",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702630074"
},
"total": 444.80413626300003,
"count": 1,
"self": 0.4870409150000796,
"children": {
"run_training.setup": {
"total": 0.07239504699998633,
"count": 1,
"self": 0.07239504699998633
},
"TrainerController.start_learning": {
"total": 444.24470030099997,
"count": 1,
"self": 0.5355187359849651,
"children": {
"TrainerController._reset_env": {
"total": 3.69143981000002,
"count": 1,
"self": 3.69143981000002
},
"TrainerController.advance": {
"total": 439.92845349001516,
"count": 18198,
"self": 0.2570292780108048,
"children": {
"env_step": {
"total": 439.67142421200435,
"count": 18198,
"self": 288.2450769260138,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.1591237069921,
"count": 18198,
"self": 1.453423126989719,
"children": {
"TorchPolicy.evaluate": {
"total": 149.70570058000237,
"count": 18198,
"self": 149.70570058000237
}
}
},
"workers": {
"total": 0.2672235789984825,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.0808352540146,
"count": 18198,
"is_parallel": true,
"self": 219.51371472200879,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006245207999995728,
"count": 1,
"is_parallel": true,
"self": 0.004308913000045322,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019362949999504053,
"count": 10,
"is_parallel": true,
"self": 0.0019362949999504053
}
}
},
"UnityEnvironment.step": {
"total": 0.04217229400001088,
"count": 1,
"is_parallel": true,
"self": 0.002236696999943888,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040632499997173,
"count": 1,
"is_parallel": true,
"self": 0.00040632499997173
},
"communicator.exchange": {
"total": 0.03585358000009364,
"count": 1,
"is_parallel": true,
"self": 0.03585358000009364
},
"steps_from_proto": {
"total": 0.003675692000001618,
"count": 1,
"is_parallel": true,
"self": 0.00038448299983429024,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0032912090001673278,
"count": 10,
"is_parallel": true,
"self": 0.0032912090001673278
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 223.5671205320058,
"count": 18197,
"is_parallel": true,
"self": 10.752959727988582,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2784543730103906,
"count": 18197,
"is_parallel": true,
"self": 5.2784543730103906
},
"communicator.exchange": {
"total": 173.8677475130031,
"count": 18197,
"is_parallel": true,
"self": 173.8677475130031
},
"steps_from_proto": {
"total": 33.667958918003706,
"count": 18197,
"is_parallel": true,
"self": 6.107246187018859,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.560712730984847,
"count": 181970,
"is_parallel": true,
"self": 27.560712730984847
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.853499993056175e-05,
"count": 1,
"self": 3.853499993056175e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.4328613589811,
"count": 674543,
"is_parallel": true,
"self": 14.176619932991684,
"children": {
"process_trajectory": {
"total": 238.33455689798905,
"count": 674543,
"is_parallel": true,
"self": 237.82487771798878,
"children": {
"RLTrainer._checkpoint": {
"total": 0.509679180000262,
"count": 4,
"is_parallel": true,
"self": 0.509679180000262
}
}
},
"_update_policy": {
"total": 181.92168452800036,
"count": 90,
"is_parallel": true,
"self": 59.20104661399375,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.7206379140066,
"count": 4587,
"is_parallel": true,
"self": 122.7206379140066
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08924972999989222,
"count": 1,
"self": 0.0009830479998527153,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08826668200003951,
"count": 1,
"self": 0.08826668200003951
}
}
}
}
}
}
}