{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5037160515785217, "min": 0.5037160515785217, "max": 1.4666719436645508, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15458.0390625, "min": 15458.0390625, "max": 44492.9609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29880.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29880.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44456467032432556, "min": -0.2122405618429184, "max": 0.4942464232444763, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 120.92159271240234, "min": -50.3010139465332, "max": 135.42352294921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 2.3462815284729004, "min": -0.3392092287540436, "max": 2.3462815284729004, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 638.1885986328125, "min": -88.87281799316406, "max": 638.1885986328125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07060688023268916, "min": 0.0651090712926026, "max": 0.07673074879304563, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9884963232576481, "min": 0.5498650498324039, "max": 1.0582271501383125, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.48689257160594807, "min": 0.00014091511534659003, "max": 0.48689257160594807, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 6.816496002483273, "min": 0.001795924982086888, "max": 6.816496002483273, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.292197569300001e-06, "min": 7.292197569300001e-06, "max": 0.0002948481017173, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010209076597020001, "min": 0.00010209076597020001, "max": 0.0032238169253944, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024307, "min": 0.1024307, "max": 0.1982827, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340298, "min": 1.4340298, "max": 2.3462176, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025282692999999996, "min": 0.00025282692999999996, "max": 0.009828441729999998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035395770199999994, "min": 0.0035395770199999994, "max": 0.10747309944, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006583294831216335, "min": 0.006583294831216335, "max": 0.3568819463253021, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09216612577438354, "min": 0.09216612577438354, "max": 2.855055570602417, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 414.44, "min": 393.1506849315069, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31083.0, "min": 16295.0, "max": 34036.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4788639783859252, "min": -0.9999750521965325, "max": 1.4874777566227648, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 110.9147983789444, "min": -31.99920167028904, "max": 120.40959817171097, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4788639783859252, "min": -0.9999750521965325, "max": 1.4874777566227648, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 110.9147983789444, "min": -31.99920167028904, "max": 120.40959817171097, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028560217526586107, "min": 0.028560217526586107, "max": 7.399959947256481, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.142016314493958, "min": 2.142016314493958, "max": 125.79931910336018, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675129198", "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1675131112" }, "total": 1914.346981532, "count": 1, "self": 0.43875693400013915, "children": { "run_training.setup": { "total": 0.10574394899992967, "count": 1, "self": 0.10574394899992967 }, "TrainerController.start_learning": { "total": 1913.8024806489998, "count": 1, "self": 1.1412718530320944, "children": { "TrainerController._reset_env": { "total": 10.156045790000007, "count": 1, "self": 10.156045790000007 }, "TrainerController.advance": { "total": 1902.4219633929677, "count": 63440, "self": 1.1385396890129869, "children": { "env_step": { "total": 1259.9011924559734, "count": 63440, "self": 1159.2281287599794, "children": { "SubprocessEnvManager._take_step": { "total": 99.95237903399584, "count": 63440, "self": 4.240421222949635, "children": { "TorchPolicy.evaluate": { "total": 95.7119578110462, "count": 62553, "self": 32.12706104000688, "children": { "TorchPolicy.sample_actions": { "total": 63.584896771039325, "count": 62553, "self": 63.584896771039325 } } } } }, "workers": { "total": 0.720684661998007, "count": 63440, "self": 0.0, "children": { "worker_root": { "total": 1910.6709323429916, "count": 63440, "is_parallel": true, "self": 843.2631228219814, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005884614000024158, "count": 1, "is_parallel": true, "self": 0.003660419000084403, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022241949999397548, "count": 8, "is_parallel": true, "self": 0.0022241949999397548 } } }, "UnityEnvironment.step": { "total": 0.11020824299998822, "count": 1, "is_parallel": true, "self": 0.0005105279998360857, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042325000003984314, "count": 1, "is_parallel": true, "self": 0.00042325000003984314 }, "communicator.exchange": { "total": 0.10774518400000943, "count": 1, "is_parallel": true, "self": 0.10774518400000943 }, "steps_from_proto": { "total": 0.0015292810001028556, "count": 1, "is_parallel": true, "self": 0.0003819470000507863, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011473340000520693, "count": 8, "is_parallel": true, "self": 0.0011473340000520693 } } } } } } }, "UnityEnvironment.step": { "total": 1067.4078095210102, "count": 63439, "is_parallel": true, "self": 26.78490433898378, "children": { "UnityEnvironment._generate_step_input": { "total": 21.66527098300901, "count": 63439, "is_parallel": true, "self": 21.66527098300901 }, "communicator.exchange": { "total": 931.1645937679934, "count": 63439, "is_parallel": true, "self": 931.1645937679934 }, "steps_from_proto": { "total": 87.793040431024, "count": 63439, "is_parallel": true, "self": 20.422689810056568, "children": { "_process_rank_one_or_two_observation": { "total": 67.37035062096743, "count": 507512, "is_parallel": true, "self": 67.37035062096743 } } } } } } } } } } }, "trainer_advance": { "total": 641.3822312479813, "count": 63440, "self": 2.0898328389417884, "children": { "process_trajectory": { "total": 139.30618183503623, "count": 63440, "self": 139.12336037803618, "children": { "RLTrainer._checkpoint": { "total": 0.18282145700004548, "count": 2, "self": 0.18282145700004548 } } }, "_update_policy": { "total": 499.98621657400327, "count": 439, "self": 189.10577444099727, "children": { "TorchPPOOptimizer.update": { "total": 310.880442133006, "count": 22803, "self": 310.880442133006 } } } } } } }, "trainer_threads": { "total": 8.810002327663824e-07, "count": 1, "self": 8.810002327663824e-07 }, "TrainerController._save_models": { "total": 0.08319873199980066, "count": 1, "self": 0.001446458999907918, "children": { "RLTrainer._checkpoint": { "total": 0.08175227299989274, "count": 1, "self": 0.08175227299989274 } } } } } } }