{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4052609205245972, "min": 1.405237078666687, "max": 1.4272716045379639, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71487.03125, "min": 68226.4921875, "max": 77929.2265625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 103.28810020876827, "min": 91.34750462107209, "max": 378.5338345864662, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49475.0, "min": 48982.0, "max": 50345.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999965.0, "min": 49884.0, "max": 1999965.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999965.0, "min": 49884.0, "max": 1999965.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3451578617095947, "min": 0.26431939005851746, "max": 2.381958246231079, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1123.33056640625, "min": 34.890159606933594, "max": 1269.583740234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5064208889555086, "min": 1.7049539116295902, "max": 3.8355419635772705, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1679.5756058096886, "min": 225.0539163351059, "max": 2009.807716012001, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5064208889555086, "min": 1.7049539116295902, "max": 3.8355419635772705, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1679.5756058096886, "min": 225.0539163351059, "max": 2009.807716012001, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.013880670529761118, "min": 0.012403521597540627, "max": 0.021841133466659814, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.027761341059522236, "min": 0.024807043195081254, "max": 0.06317608293902595, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04488476297507683, "min": 0.020105578067402045, "max": 0.05795222253849109, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08976952595015367, "min": 0.04021115613480409, "max": 0.16843547771374384, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.273823575425e-06, "min": 4.273823575425e-06, "max": 0.000295327726557425, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.54764715085e-06, "min": 8.54764715085e-06, "max": 0.0008443800185399997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10142457500000002, "min": 0.10142457500000002, "max": 0.19844257500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20284915000000003, "min": 0.20284915000000003, "max": 0.5814600000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.108629250000001e-05, "min": 8.108629250000001e-05, "max": 0.0049222844925, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016217258500000003, "min": 0.00016217258500000003, "max": 0.014074854000000001, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675751919", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675754655" }, "total": 2735.6659800449997, "count": 1, "self": 0.7406236689998877, "children": { "run_training.setup": { "total": 0.11954431399999521, "count": 1, "self": 0.11954431399999521 }, "TrainerController.start_learning": { "total": 2734.805812062, "count": 1, "self": 5.137922469864861, "children": { "TrainerController._reset_env": { "total": 11.107286851000026, "count": 1, "self": 11.107286851000026 }, "TrainerController.advance": { "total": 2718.4196289161346, "count": 231663, "self": 5.316599241158656, "children": { "env_step": { "total": 2118.616382736075, "count": 231663, "self": 1766.686924614044, "children": { "SubprocessEnvManager._take_step": { "total": 348.58468683395085, "count": 231663, "self": 18.22460880600852, "children": { "TorchPolicy.evaluate": { "total": 330.36007802794234, "count": 223029, "self": 81.47455989385344, "children": { "TorchPolicy.sample_actions": { "total": 248.8855181340889, "count": 223029, "self": 248.8855181340889 } } } } }, "workers": { "total": 3.34477128808021, "count": 231663, "self": 0.0, "children": { "worker_root": { "total": 2724.661864466051, "count": 231663, "is_parallel": true, "self": 1294.284258982139, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022358390001500084, "count": 1, "is_parallel": true, "self": 0.0003682700003082573, "children": { "_process_rank_one_or_two_observation": { "total": 0.001867568999841751, "count": 2, "is_parallel": true, "self": 0.001867568999841751 } } }, "UnityEnvironment.step": { "total": 0.036623979999831136, "count": 1, "is_parallel": true, "self": 0.00033556999983375135, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020495700005085382, "count": 1, "is_parallel": true, "self": 0.00020495700005085382 }, "communicator.exchange": { "total": 0.03520993099982661, "count": 1, "is_parallel": true, "self": 0.03520993099982661 }, "steps_from_proto": { "total": 0.0008735220001199195, "count": 1, "is_parallel": true, "self": 0.0002872539998861612, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005862680002337584, "count": 2, "is_parallel": true, "self": 0.0005862680002337584 } } } } } } }, "UnityEnvironment.step": { "total": 1430.3776054839122, "count": 231662, "is_parallel": true, "self": 42.35871159697376, "children": { "UnityEnvironment._generate_step_input": { "total": 90.79975018805476, "count": 231662, "is_parallel": true, "self": 90.79975018805476 }, "communicator.exchange": { "total": 1187.0525866178793, "count": 231662, "is_parallel": true, "self": 1187.0525866178793 }, "steps_from_proto": { "total": 110.16655708100438, "count": 231662, "is_parallel": true, "self": 44.77645356901439, "children": { "_process_rank_one_or_two_observation": { "total": 65.39010351198999, "count": 463324, "is_parallel": true, "self": 65.39010351198999 } } } } } } } } } } }, "trainer_advance": { "total": 594.4866469389005, "count": 231663, "self": 8.49190968284256, "children": { "process_trajectory": { "total": 180.13860233605715, "count": 231663, "self": 178.9146964910576, "children": { "RLTrainer._checkpoint": { "total": 1.2239058449995355, "count": 10, "self": 1.2239058449995355 } } }, "_update_policy": { "total": 405.85613492000084, "count": 96, "self": 345.23522319599806, "children": { "TorchPPOOptimizer.update": { "total": 60.62091172400278, "count": 2880, "self": 60.62091172400278 } } } } } } }, "trainer_threads": { "total": 9.40000063565094e-07, "count": 1, "self": 9.40000063565094e-07 }, "TrainerController._save_models": { "total": 0.14097288500033756, "count": 1, "self": 0.0038351900002453476, "children": { "RLTrainer._checkpoint": { "total": 0.1371376950000922, "count": 1, "self": 0.1371376950000922 } } } } } } }