{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5553489923477173, "min": 0.5553489923477173, "max": 1.3712724447250366, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16758.2109375, "min": 16758.2109375, "max": 41598.921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29940.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29940.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2689127027988434, "min": -0.0872347503900528, "max": 0.2689127027988434, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 69.64839172363281, "min": -20.93634033203125, "max": 69.64839172363281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022072983905673027, "min": 0.006909343414008617, "max": 0.4474110007286072, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.716902732849121, "min": 1.7678422927856445, "max": 106.03640747070312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06849379548276331, "min": 0.0652461227737429, "max": 0.07396565231805047, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9589131367586864, "min": 0.6504622445442398, "max": 1.109484784770757, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014191582177383158, "min": 0.0005619208560341938, "max": 0.014191582177383158, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1986821504833642, "min": 0.007866891984478713, "max": 0.2094002794571376, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.24916901221429e-06, "min": 7.24916901221429e-06, "max": 0.0002948761350412889, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010148836617100006, "min": 0.00010148836617100006, "max": 0.0036347539884153983, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241635714285716, "min": 0.10241635714285716, "max": 0.19829204444444448, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338290000000002, "min": 1.4338290000000002, "max": 2.6115846, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025139407857142877, "min": 0.00025139407857142877, "max": 0.00982937524, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035195171000000024, "min": 0.0035195171000000024, "max": 0.12117730154000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012161307036876678, "min": 0.011707554571330547, "max": 0.4057108163833618, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1702582985162735, "min": 0.1702582985162735, "max": 3.651397466659546, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 522.6140350877193, "min": 522.6140350877193, "max": 998.1379310344828, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29789.0, "min": 16611.0, "max": 32920.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1614912063406224, "min": -0.9296069489470844, "max": 1.1614912063406224, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 66.20499876141548, "min": -30.65360176563263, "max": 66.20499876141548, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1614912063406224, "min": -0.9296069489470844, "max": 1.1614912063406224, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 66.20499876141548, "min": -30.65360176563263, "max": 66.20499876141548, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06586148146577711, "min": 0.06586148146577711, "max": 8.006500035524368, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.754104443549295, "min": 3.6697243319358677, "max": 136.11050060391426, "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": "1684800738", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684802931" }, "total": 2192.906165839, "count": 1, "self": 0.47448447100032354, "children": { "run_training.setup": { "total": 0.037876761999996233, "count": 1, "self": 0.037876761999996233 }, "TrainerController.start_learning": { "total": 2192.393804606, "count": 1, "self": 1.498494276969268, "children": { "TrainerController._reset_env": { "total": 4.415871741000046, "count": 1, "self": 4.415871741000046 }, "TrainerController.advance": { "total": 2186.386978914031, "count": 63479, "self": 1.4853020870609726, "children": { "env_step": { "total": 1539.0212503669932, "count": 63479, "self": 1422.5305883250312, "children": { "SubprocessEnvManager._take_step": { "total": 115.62372424297928, "count": 63479, "self": 5.109395967995283, "children": { "TorchPolicy.evaluate": { "total": 110.514328274984, "count": 62571, "self": 110.514328274984 } } }, "workers": { "total": 0.8669377989826899, "count": 63479, "self": 0.0, "children": { "worker_root": { "total": 2186.9798168300313, "count": 63479, "is_parallel": true, "self": 885.949442773079, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018862319999470856, "count": 1, "is_parallel": true, "self": 0.000584677000119882, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013015549998272036, "count": 8, "is_parallel": true, "self": 0.0013015549998272036 } } }, "UnityEnvironment.step": { "total": 0.08947725999996692, "count": 1, "is_parallel": true, "self": 0.0005890919999274047, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005082959999072045, "count": 1, "is_parallel": true, "self": 0.0005082959999072045 }, "communicator.exchange": { "total": 0.08011771400003909, "count": 1, "is_parallel": true, "self": 0.08011771400003909 }, "steps_from_proto": { "total": 0.008262158000093223, "count": 1, "is_parallel": true, "self": 0.0004460970003492548, "children": { "_process_rank_one_or_two_observation": { "total": 0.007816060999743968, "count": 8, "is_parallel": true, "self": 0.007816060999743968 } } } } } } }, "UnityEnvironment.step": { "total": 1301.0303740569523, "count": 63478, "is_parallel": true, "self": 32.45844834696322, "children": { "UnityEnvironment._generate_step_input": { "total": 24.882303714988666, "count": 63478, "is_parallel": true, "self": 24.882303714988666 }, "communicator.exchange": { "total": 1137.0955325470188, "count": 63478, "is_parallel": true, "self": 1137.0955325470188 }, "steps_from_proto": { "total": 106.59408944798145, "count": 63478, "is_parallel": true, "self": 22.416734550168826, "children": { "_process_rank_one_or_two_observation": { "total": 84.17735489781262, "count": 507824, "is_parallel": true, "self": 84.17735489781262 } } } } } } } } } } }, "trainer_advance": { "total": 645.8804264599767, "count": 63479, "self": 2.818831004911658, "children": { "process_trajectory": { "total": 115.41120657106285, "count": 63479, "self": 115.21042983506254, "children": { "RLTrainer._checkpoint": { "total": 0.2007767360003072, "count": 2, "self": 0.2007767360003072 } } }, "_update_policy": { "total": 527.6503888840022, "count": 456, "self": 341.9137686080203, "children": { "TorchPPOOptimizer.update": { "total": 185.73662027598186, "count": 22734, "self": 185.73662027598186 } } } } } } }, "trainer_threads": { "total": 1.1429997357481625e-06, "count": 1, "self": 1.1429997357481625e-06 }, "TrainerController._save_models": { "total": 0.09245853099992019, "count": 1, "self": 0.0014060630001040408, "children": { "RLTrainer._checkpoint": { "total": 0.09105246799981614, "count": 1, "self": 0.09105246799981614 } } } } } } }