{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 0.5726810097694397, "min": 0.5726810097694397, "max": 1.4213045835494995, "count": 331 }, "Worm.Policy.Entropy.sum": { "value": 17180.4296875, "min": 17180.4296875, "max": 42639.13671875, "count": 331 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 331 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 331 }, "Worm.Step.mean": { "value": 9989000.0, "min": 89000.0, "max": 9989000.0, "count": 331 }, "Worm.Step.sum": { "value": 9989000.0, "min": 89000.0, "max": 9989000.0, "count": 331 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 267.6130065917969, "min": 0.03357606381177902, "max": 268.85986328125, "count": 331 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 8028.390625, "min": 1.0072818994522095, "max": 8065.7958984375, "count": 331 }, "Worm.Environment.CumulativeReward.mean": { "value": 1334.1102701822917, "min": 0.4373771018510587, "max": 1349.6483764648438, "count": 331 }, "Worm.Environment.CumulativeReward.sum": { "value": 40023.30810546875, "min": 12.683935953680702, "max": 40489.45129394531, "count": 331 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 1334.1102701822917, "min": 0.4373771018510587, "max": 1349.6483764648438, "count": 331 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 40023.30810546875, "min": 12.683935953680702, "max": 40489.45129394531, "count": 331 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 331 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 331 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.01681270562611254, "min": 0.011412449494898846, "max": 0.02326744109329108, "count": 330 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.01681270562611254, "min": 0.011412449494898846, "max": 0.02326744109329108, "count": 330 }, "Worm.Losses.ValueLoss.mean": { "value": 11.543587639218284, "min": 0.0017147210282495334, "max": 15.45382125037057, "count": 330 }, "Worm.Losses.ValueLoss.sum": { "value": 11.543587639218284, "min": 0.0017147210282495334, "max": 15.45382125037057, "count": 330 }, "Worm.Policy.LearningRate.mean": { "value": 1.200099600000001e-06, "min": 1.200099600000001e-06, "max": 0.0002973000008999999, "count": 330 }, "Worm.Policy.LearningRate.sum": { "value": 1.200099600000001e-06, "min": 1.200099600000001e-06, "max": 0.0002973000008999999, "count": 330 }, "Worm.Policy.Epsilon.mean": { "value": 0.10039999999999998, "min": 0.10039999999999998, "max": 0.1991, "count": 330 }, "Worm.Policy.Epsilon.sum": { "value": 0.10039999999999998, "min": 0.10039999999999998, "max": 0.1991, "count": 330 }, "Worm.Policy.Beta.mean": { "value": 2.996000000000002e-05, "min": 2.996000000000002e-05, "max": 0.00495509, "count": 330 }, "Worm.Policy.Beta.sum": { "value": 2.996000000000002e-05, "min": 2.996000000000002e-05, "max": 0.00495509, "count": 330 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1656186219", "python_version": "3.8.13 (default, Mar 28 2022, 11:38:47) \n[GCC 7.5.0]", "command_line_arguments": "/home/fork/anaconda3/bin/mlagents-learn config/ppo/Worm.yaml --env=trained-envs-executables/Linux/Worm/Worm --run-id=Worm Training --resume", "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": "1.23.0", "end_time_seconds": "1656195671" }, "total": 9451.699728936, "count": 1, "self": 0.32004495700130065, "children": { "run_training.setup": { "total": 0.017476320999776362, "count": 1, "self": 0.017476320999776362 }, "TrainerController.start_learning": { "total": 9451.362207658, "count": 1, "self": 19.058778397335118, "children": { "TrainerController._reset_env": { "total": 5.39241804600033, "count": 1, "self": 5.39241804600033 }, "TrainerController.advance": { "total": 9426.789333705665, "count": 995000, "self": 18.7491508264211, "children": { "env_step": { "total": 7629.01990378858, "count": 995000, "self": 6359.427056807752, "children": { "SubprocessEnvManager._take_step": { "total": 1257.3940827167958, "count": 995000, "self": 75.58869363709937, "children": { "TorchPolicy.evaluate": { "total": 1181.8053890796964, "count": 995000, "self": 334.06699615589014, "children": { "TorchPolicy.sample_actions": { "total": 847.7383929238063, "count": 995000, "self": 847.7383929238063 } } } } }, "workers": { "total": 12.198764264032434, "count": 995000, "self": 0.0, "children": { "worker_root": { "total": 9423.339519103354, "count": 995000, "is_parallel": true, "self": 4111.780137258689, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006321539999589731, "count": 1, "is_parallel": true, "self": 0.0001999920000343991, "children": { "_process_rank_one_or_two_observation": { "total": 0.00043216199992457405, "count": 2, "is_parallel": true, "self": 0.00043216199992457405 } } }, "UnityEnvironment.step": { "total": 0.02916383699994185, "count": 1, "is_parallel": true, "self": 0.00013833599996360135, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002955889999611827, "count": 1, "is_parallel": true, "self": 0.0002955889999611827 }, "communicator.exchange": { "total": 0.028437583000140876, "count": 1, "is_parallel": true, "self": 0.028437583000140876 }, "steps_from_proto": { "total": 0.0002923289998761902, "count": 1, "is_parallel": true, "self": 0.00011298499930489925, "children": { "_process_rank_one_or_two_observation": { "total": 0.00017934400057129096, "count": 2, "is_parallel": true, "self": 0.00017934400057129096 } } } } } } }, "UnityEnvironment.step": { "total": 5311.559381844665, "count": 994999, "is_parallel": true, "self": 128.78026232249613, "children": { "UnityEnvironment._generate_step_input": { "total": 193.3560841044391, "count": 994999, "is_parallel": true, "self": 193.3560841044391 }, "communicator.exchange": { "total": 4695.107448400225, "count": 994999, "is_parallel": true, "self": 4695.107448400225 }, "steps_from_proto": { "total": 294.31558701750464, "count": 994999, "is_parallel": true, "self": 112.94182494571714, "children": { "_process_rank_one_or_two_observation": { "total": 181.3737620717875, "count": 1989998, "is_parallel": true, "self": 181.3737620717875 } } } } } } } } } } }, "trainer_advance": { "total": 1779.0202790906637, "count": 995000, "self": 22.340899760353295, "children": { "process_trajectory": { "total": 465.350640757315, "count": 995000, "self": 462.2231368383136, "children": { "RLTrainer._checkpoint": { "total": 3.127503919001356, "count": 20, "self": 3.127503919001356 } } }, "_update_policy": { "total": 1291.3287385729955, "count": 331, "self": 977.4246966580254, "children": { "TorchPPOOptimizer.update": { "total": 313.9040419149701, "count": 13902, "self": 313.9040419149701 } } } } } } }, "trainer_threads": { "total": 8.299994078697637e-07, "count": 1, "self": 8.299994078697637e-07 }, "TrainerController._save_models": { "total": 0.1216766790003021, "count": 1, "self": 0.0020022699991386617, "children": { "RLTrainer._checkpoint": { "total": 0.11967440900116344, "count": 1, "self": 0.11967440900116344 } } } } } } }