yhna's picture
First Push
8ef9655
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9591020941734314,
"min": 0.9512712359428406,
"max": 2.858474016189575,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9811.6142578125,
"min": 9381.2744140625,
"max": 29493.734375,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.701272010803223,
"min": 0.4677414894104004,
"max": 13.701272010803223,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2795.0595703125,
"min": 90.74185180664062,
"max": 2795.0595703125,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06830695194897571,
"min": 0.06077448416678331,
"max": 0.07491114890549842,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.34153475974487857,
"min": 0.2617668808990286,
"max": 0.37455574452749213,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1679887422451786,
"min": 0.1319428372308703,
"max": 0.2724481985411223,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.839943711225893,
"min": 0.5277713489234812,
"max": 1.330173640128444,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.288098237333331e-06,
"min": 5.288098237333331e-06,
"max": 0.00029458800180399996,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.6440491186666655e-05,
"min": 2.6440491186666655e-05,
"max": 0.0014234400255199997,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10176266666666667,
"min": 0.10176266666666667,
"max": 0.198196,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5088133333333333,
"min": 0.42025066666666666,
"max": 0.97448,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.795706666666662e-05,
"min": 9.795706666666662e-05,
"max": 0.0049099804000000006,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004897853333333331,
"min": 0.0004897853333333331,
"max": 0.023726551999999998,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.89090909090909,
"min": 4.204545454545454,
"max": 26.89090909090909,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1479.0,
"min": 185.0,
"max": 1479.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.89090909090909,
"min": 4.204545454545454,
"max": 26.89090909090909,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1479.0,
"min": 185.0,
"max": 1479.0,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687999423",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --force --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688000611"
},
"total": 1188.1082784259997,
"count": 1,
"self": 0.5381953649996376,
"children": {
"run_training.setup": {
"total": 0.05800640600000406,
"count": 1,
"self": 0.05800640600000406
},
"TrainerController.start_learning": {
"total": 1187.512076655,
"count": 1,
"self": 1.4700940769942008,
"children": {
"TrainerController._reset_env": {
"total": 1.173961203999852,
"count": 1,
"self": 1.173961203999852
},
"TrainerController.advance": {
"total": 1184.5726741710057,
"count": 27341,
"self": 0.7288449550035239,
"children": {
"env_step": {
"total": 1183.8438292160022,
"count": 27341,
"self": 963.5517174460572,
"children": {
"SubprocessEnvManager._take_step": {
"total": 219.55688464799437,
"count": 27341,
"self": 5.274280279986215,
"children": {
"TorchPolicy.evaluate": {
"total": 214.28260436800815,
"count": 27341,
"self": 214.28260436800815
}
}
},
"workers": {
"total": 0.7352271219506292,
"count": 27341,
"self": 0.0,
"children": {
"worker_root": {
"total": 1183.2922816159962,
"count": 27341,
"is_parallel": true,
"self": 649.8470923320085,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023338060000241967,
"count": 1,
"is_parallel": true,
"self": 0.0006931350003469561,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016406709996772406,
"count": 10,
"is_parallel": true,
"self": 0.0016406709996772406
}
}
},
"UnityEnvironment.step": {
"total": 0.04819599899997229,
"count": 1,
"is_parallel": true,
"self": 0.0008511540002018592,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003737219999493391,
"count": 1,
"is_parallel": true,
"self": 0.0003737219999493391
},
"communicator.exchange": {
"total": 0.04431456599991179,
"count": 1,
"is_parallel": true,
"self": 0.04431456599991179
},
"steps_from_proto": {
"total": 0.0026565569999092986,
"count": 1,
"is_parallel": true,
"self": 0.0006314969994036801,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020250600005056185,
"count": 10,
"is_parallel": true,
"self": 0.0020250600005056185
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 533.4451892839877,
"count": 27340,
"is_parallel": true,
"self": 22.70352336002793,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.46504832403025,
"count": 27340,
"is_parallel": true,
"self": 11.46504832403025
},
"communicator.exchange": {
"total": 424.5874717469703,
"count": 27340,
"is_parallel": true,
"self": 424.5874717469703
},
"steps_from_proto": {
"total": 74.6891458529592,
"count": 27340,
"is_parallel": true,
"self": 15.187393732898727,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.50175212006047,
"count": 273400,
"is_parallel": true,
"self": 59.50175212006047
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00031334900040747016,
"count": 1,
"self": 0.00031334900040747016,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1175.4229038440028,
"count": 976194,
"is_parallel": true,
"self": 25.637666399025875,
"children": {
"process_trajectory": {
"total": 562.3693318599767,
"count": 976194,
"is_parallel": true,
"self": 558.2286451739767,
"children": {
"RLTrainer._checkpoint": {
"total": 4.140686685999981,
"count": 6,
"is_parallel": true,
"self": 4.140686685999981
}
}
},
"_update_policy": {
"total": 587.4159055850002,
"count": 136,
"is_parallel": true,
"self": 130.831917281017,
"children": {
"TorchPPOOptimizer.update": {
"total": 456.58398830398323,
"count": 6930,
"is_parallel": true,
"self": 456.58398830398323
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2950338539999393,
"count": 1,
"self": 0.0069579300002260425,
"children": {
"RLTrainer._checkpoint": {
"total": 0.28807592399971327,
"count": 1,
"self": 0.28807592399971327
}
}
}
}
}
}
}