{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2807066738605499, "min": 0.2807066738605499, "max": 1.3785403966903687, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8416.708984375, "min": 8416.708984375, "max": 41819.40234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29902.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29902.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5903724431991577, "min": -0.08363796770572662, "max": 0.6943753361701965, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.12353515625, "min": -20.07311248779297, "max": 200.67446899414062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026276985183358192, "min": 0.0030761195812374353, "max": 0.4331190586090088, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.305001735687256, "min": 0.8274761438369751, "max": 102.64921569824219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06582811953871985, "min": 0.06516470028214999, "max": 0.07245532434397897, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.921593673542078, "min": 0.5026240653136609, "max": 1.0777334175586208, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014429506556486713, "min": 0.0004922993454828314, "max": 0.017590257472225597, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20201309179081398, "min": 0.004430694109345483, "max": 0.24626360461115834, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.540533200807144e-06, "min": 7.540533200807144e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010556746481130002, "min": 0.00010556746481130002, "max": 0.0032573925142026, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251347857142858, "min": 0.10251347857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351887, "min": 1.3886848, "max": 2.4857974000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026109650928571434, "min": 0.00026109650928571434, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036553511300000006, "min": 0.0036553511300000006, "max": 0.10861116025999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014858576469123363, "min": 0.014858576469123363, "max": 0.7446269989013672, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20802007615566254, "min": 0.20802007615566254, "max": 5.21238899230957, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 288.6185567010309, "min": 278.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27996.0, "min": 16829.0, "max": 32201.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6265728971144806, "min": -0.9999871489501768, "max": 1.702578624330678, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.15099812299013, "min": -31.99920167028904, "max": 186.70099716633558, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6265728971144806, "min": -0.9999871489501768, "max": 1.702578624330678, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.15099812299013, "min": -31.99920167028904, "max": 186.70099716633558, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04452478174365145, "min": 0.04452478174365145, "max": 14.489005896098474, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.274379047390539, "min": 4.274379047390539, "max": 246.31310023367405, "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": "1678970031", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1678972312" }, "total": 2281.0831764779996, "count": 1, "self": 0.4917932069993185, "children": { "run_training.setup": { "total": 0.17520433299978322, "count": 1, "self": 0.17520433299978322 }, "TrainerController.start_learning": { "total": 2280.4161789380005, "count": 1, "self": 1.4639609029768508, "children": { "TrainerController._reset_env": { "total": 7.994707173999814, "count": 1, "self": 7.994707173999814 }, "TrainerController.advance": { "total": 2270.8678907210237, "count": 63996, "self": 1.5147190421225787, "children": { "env_step": { "total": 1617.6987452108656, "count": 63996, "self": 1502.2290419068827, "children": { "SubprocessEnvManager._take_step": { "total": 114.58311953106886, "count": 63996, "self": 5.050820741978896, "children": { "TorchPolicy.evaluate": { "total": 109.53229878908996, "count": 62554, "self": 109.53229878908996 } } }, "workers": { "total": 0.8865837729140367, "count": 63996, "self": 0.0, "children": { "worker_root": { "total": 2275.3220508680847, "count": 63996, "is_parallel": true, "self": 894.4157313070355, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00265867200005232, "count": 1, "is_parallel": true, "self": 0.0009147169998868776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017439550001654425, "count": 8, "is_parallel": true, "self": 0.0017439550001654425 } } }, "UnityEnvironment.step": { "total": 0.04867095600002358, "count": 1, "is_parallel": true, "self": 0.0005179599997973128, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004727870000351686, "count": 1, "is_parallel": true, "self": 0.0004727870000351686 }, "communicator.exchange": { "total": 0.04597873600005187, "count": 1, "is_parallel": true, "self": 0.04597873600005187 }, "steps_from_proto": { "total": 0.0017014730001392309, "count": 1, "is_parallel": true, "self": 0.00038074600024629035, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013207269998929405, "count": 8, "is_parallel": true, "self": 0.0013207269998929405 } } } } } } }, "UnityEnvironment.step": { "total": 1380.9063195610493, "count": 63995, "is_parallel": true, "self": 31.27054110609606, "children": { "UnityEnvironment._generate_step_input": { "total": 23.63493371599634, "count": 63995, "is_parallel": true, "self": 23.63493371599634 }, "communicator.exchange": { "total": 1230.9208444089268, "count": 63995, "is_parallel": true, "self": 1230.9208444089268 }, "steps_from_proto": { "total": 95.08000033003009, "count": 63995, "is_parallel": true, "self": 20.697079896788637, "children": { "_process_rank_one_or_two_observation": { "total": 74.38292043324145, "count": 511960, "is_parallel": true, "self": 74.38292043324145 } } } } } } } } } } }, "trainer_advance": { "total": 651.6544264680356, "count": 63996, "self": 2.690925970047374, "children": { "process_trajectory": { "total": 127.45521108198409, "count": 63996, "self": 127.18534352098413, "children": { "RLTrainer._checkpoint": { "total": 0.26986756099995546, "count": 2, "self": 0.26986756099995546 } } }, "_update_policy": { "total": 521.5082894160041, "count": 447, "self": 333.6191637679849, "children": { "TorchPPOOptimizer.update": { "total": 187.88912564801922, "count": 22836, "self": 187.88912564801922 } } } } } } }, "trainer_threads": { "total": 1.2669997886405326e-06, "count": 1, "self": 1.2669997886405326e-06 }, "TrainerController._save_models": { "total": 0.08961887300029048, "count": 1, "self": 0.0014015870001458097, "children": { "RLTrainer._checkpoint": { "total": 0.08821728600014467, "count": 1, "self": 0.08821728600014467 } } } } } } }