{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5800516605377197, "min": 0.5593442916870117, "max": 1.4775760173797607, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17466.515625, "min": 16825.076171875, "max": 44823.74609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989959.0, "min": 29952.0, "max": 989959.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989959.0, "min": 29952.0, "max": 989959.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.29381003975868225, "min": -0.15899990499019623, "max": 0.31088945269584656, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 75.80299377441406, "min": -37.68297576904297, "max": 80.20948028564453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05892396345734596, "min": -0.006211516913026571, "max": 0.3885716199874878, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 15.202383041381836, "min": -1.6025713682174683, "max": 92.09147644042969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06719951123706489, "min": 0.06556217966937829, "max": 0.07304959680398546, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9407931573189083, "min": 0.5000619709671705, "max": 1.063710346779165, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011482207912582244, "min": 4.705453232804075e-05, "max": 0.013816381514534088, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16075091077615142, "min": 0.0006117089202645298, "max": 0.19342934120347724, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.514668923714288e-06, "min": 7.514668923714288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010520536493200003, "min": 0.00010520536493200003, "max": 0.0034900441366519995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250485714285715, "min": 0.10250485714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.435068, "min": 1.3886848, "max": 2.4859092000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026023522857142865, "min": 0.00026023522857142865, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003643293200000001, "min": 0.003643293200000001, "max": 0.11634846520000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009792380966246128, "min": 0.009792380966246128, "max": 0.3346693217754364, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13709333539009094, "min": 0.13709333539009094, "max": 2.3426852226257324, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 544.4310344827586, "min": 508.75925925925924, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31577.0, "min": 15984.0, "max": 32731.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1106551366633381, "min": -1.0000000521540642, "max": 1.2319036723562964, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.41799792647362, "min": -30.753801688551903, "max": 66.52279830724001, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1106551366633381, "min": -1.0000000521540642, "max": 1.2319036723562964, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.41799792647362, "min": -30.753801688551903, "max": 66.52279830724001, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05447464144777643, "min": 0.05393904113184868, "max": 7.047320468351245, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.159529203971033, "min": 2.9127082211198285, "max": 112.75712749361992, "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": "1793032785", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1793034802" }, "total": 2016.7191739390003, "count": 1, "self": 0.4792098050002096, "children": { "run_training.setup": { "total": 0.02508611899997959, "count": 1, "self": 0.02508611899997959 }, "TrainerController.start_learning": { "total": 2016.214878015, "count": 1, "self": 1.2422510149726804, "children": { "TrainerController._reset_env": { "total": 2.145697315999996, "count": 1, "self": 2.145697315999996 }, "TrainerController.advance": { "total": 2012.7370418740277, "count": 63344, "self": 1.2978889280907424, "children": { "env_step": { "total": 1424.385602332944, "count": 63344, "self": 1280.1386804329607, "children": { "SubprocessEnvManager._take_step": { "total": 143.4965359130565, "count": 63344, "self": 4.459700640071787, "children": { "TorchPolicy.evaluate": { "total": 139.03683527298472, "count": 62555, "self": 139.03683527298472 } } }, "workers": { "total": 0.7503859869268581, "count": 63344, "self": 0.0, "children": { "worker_root": { "total": 2012.9071545039867, "count": 63344, "is_parallel": true, "self": 838.9027261029337, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018613370000366558, "count": 1, "is_parallel": true, "self": 0.0006175260000418348, "children": { "_process_rank_one_or_two_observation": { "total": 0.001243810999994821, "count": 8, "is_parallel": true, "self": 0.001243810999994821 } } }, "UnityEnvironment.step": { "total": 0.05333129900009226, "count": 1, "is_parallel": true, "self": 0.0006133400001999689, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005105340001136938, "count": 1, "is_parallel": true, "self": 0.0005105340001136938 }, "communicator.exchange": { "total": 0.048633502999791745, "count": 1, "is_parallel": true, "self": 0.048633502999791745 }, "steps_from_proto": { "total": 0.003573921999986851, "count": 1, "is_parallel": true, "self": 0.0003618610001012712, "children": { "_process_rank_one_or_two_observation": { "total": 0.00321206099988558, "count": 8, "is_parallel": true, "self": 0.00321206099988558 } } } } } } }, "UnityEnvironment.step": { "total": 1174.004428401053, "count": 63343, "is_parallel": true, "self": 32.892029369895454, "children": { "UnityEnvironment._generate_step_input": { "total": 23.20613698607258, "count": 63343, "is_parallel": true, "self": 23.20613698607258 }, "communicator.exchange": { "total": 1017.603843689033, "count": 63343, "is_parallel": true, "self": 1017.603843689033 }, "steps_from_proto": { "total": 100.30241835605193, "count": 63343, "is_parallel": true, "self": 19.87803609194316, "children": { "_process_rank_one_or_two_observation": { "total": 80.42438226410877, "count": 506744, "is_parallel": true, "self": 80.42438226410877 } } } } } } } } } } }, "trainer_advance": { "total": 587.0535506129929, "count": 63344, "self": 2.397838187054276, "children": { "process_trajectory": { "total": 104.74569505693626, "count": 63344, "self": 104.56738614093638, "children": { "RLTrainer._checkpoint": { "total": 0.17830891599987808, "count": 2, "self": 0.17830891599987808 } } }, "_update_policy": { "total": 479.9100173690024, "count": 450, "self": 253.2348347899947, "children": { "TorchPPOOptimizer.update": { "total": 226.6751825790077, "count": 22782, "self": 226.6751825790077 } } } } } } }, "trainer_threads": { "total": 9.709997357276734e-07, "count": 1, "self": 9.709997357276734e-07 }, "TrainerController._save_models": { "total": 0.0898868389999734, "count": 1, "self": 0.0010953810001410602, "children": { "RLTrainer._checkpoint": { "total": 0.08879145799983235, "count": 1, "self": 0.08879145799983235 } } } } } } }