{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8099809885025024, "min": 0.5570735335350037, "max": 1.4301304817199707, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 24260.55078125, "min": 16640.900390625, "max": 43384.4375, "count": 33 }, "Pyramids.Step.mean": { "value": 989895.0, "min": 29952.0, "max": 989895.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989895.0, "min": 29952.0, "max": 989895.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07085061073303223, "min": -0.09702851623296738, "max": 0.3550646901130676, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -17.074996948242188, "min": -23.28684425354004, "max": 95.15733337402344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.2467518150806427, "min": -4.149189472198486, "max": 2.8301491737365723, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -59.467185974121094, "min": -1045.595703125, "max": 758.47998046875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06598078415429752, "min": 0.0638285303618802, "max": 0.07223936065394596, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9237309781601654, "min": 0.46930003225075445, "max": 1.0345382941921022, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.1563212539409246, "min": 0.00043586424553891255, "max": 7.5306195433574326, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 2.1884975551729444, "min": 0.004794506700928038, "max": 105.42867360700406, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.391218964864288e-06, "min": 7.391218964864288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010347706550810003, "min": 0.00010347706550810003, "max": 0.0031413215528929006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246370714285714, "min": 0.10246370714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344919, "min": 1.3691136000000002, "max": 2.3471071, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002561243435714287, "min": 0.0002561243435714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035857408100000016, "min": 0.0035857408100000016, "max": 0.10473599928999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.003970048855990171, "min": 0.003537293989211321, "max": 0.39252251386642456, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.055580683052539825, "min": 0.04952211678028107, "max": 2.747657537460327, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 946.1935483870968, "min": 461.1666666666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29332.0, "min": 15984.0, "max": 33175.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.7532000508039228, "min": -1.0000000521540642, "max": 1.2472872419790788, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -23.349201574921608, "min": -32.000001668930054, "max": 81.55679872632027, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.7532000508039228, "min": -1.0000000521540642, "max": 1.2472872419790788, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -23.349201574921608, "min": -32.000001668930054, "max": 81.55679872632027, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03745276443594541, "min": 0.03745276443594541, "max": 7.801773116923869, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.1610356975143077, "min": 1.1610356975143077, "max": 124.8283698707819, "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": "1710584248", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710586542" }, "total": 2293.355035107, "count": 1, "self": 0.4967895539998608, "children": { "run_training.setup": { "total": 0.05331629900001644, "count": 1, "self": 0.05331629900001644 }, "TrainerController.start_learning": { "total": 2292.804929254, "count": 1, "self": 1.289001316991289, "children": { "TrainerController._reset_env": { "total": 2.695360414000106, "count": 1, "self": 2.695360414000106 }, "TrainerController.advance": { "total": 2288.723647578009, "count": 63316, "self": 1.3834439219999695, "children": { "env_step": { "total": 1671.1591172130406, "count": 63316, "self": 1537.7376715890396, "children": { "SubprocessEnvManager._take_step": { "total": 132.60257589397315, "count": 63316, "self": 4.692079314982948, "children": { "TorchPolicy.evaluate": { "total": 127.9104965789902, "count": 62567, "self": 127.9104965789902 } } }, "workers": { "total": 0.8188697300279273, "count": 63316, "self": 0.0, "children": { "worker_root": { "total": 2287.521404177975, "count": 63316, "is_parallel": true, "self": 873.3598938329621, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029830769999534823, "count": 1, "is_parallel": true, "self": 0.000979865000317659, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020032119996358233, "count": 8, "is_parallel": true, "self": 0.0020032119996358233 } } }, "UnityEnvironment.step": { "total": 0.04978881199986063, "count": 1, "is_parallel": true, "self": 0.0007020989999091398, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000527425999962361, "count": 1, "is_parallel": true, "self": 0.000527425999962361 }, "communicator.exchange": { "total": 0.046488168999985646, "count": 1, "is_parallel": true, "self": 0.046488168999985646 }, "steps_from_proto": { "total": 0.00207111800000348, "count": 1, "is_parallel": true, "self": 0.00040667999951438105, "children": { "_process_rank_one_or_two_observation": { "total": 0.001664438000489099, "count": 8, "is_parallel": true, "self": 0.001664438000489099 } } } } } } }, "UnityEnvironment.step": { "total": 1414.1615103450129, "count": 63315, "is_parallel": true, "self": 34.747392043035234, "children": { "UnityEnvironment._generate_step_input": { "total": 25.14877576398908, "count": 63315, "is_parallel": true, "self": 25.14877576398908 }, "communicator.exchange": { "total": 1251.8785185069771, "count": 63315, "is_parallel": true, "self": 1251.8785185069771 }, "steps_from_proto": { "total": 102.38682403101143, "count": 63315, "is_parallel": true, "self": 20.542862439915098, "children": { "_process_rank_one_or_two_observation": { "total": 81.84396159109633, "count": 506520, "is_parallel": true, "self": 81.84396159109633 } } } } } } } } } } }, "trainer_advance": { "total": 616.1810864429683, "count": 63316, "self": 2.4923835849785974, "children": { "process_trajectory": { "total": 124.44263754999133, "count": 63316, "self": 124.23215826499131, "children": { "RLTrainer._checkpoint": { "total": 0.21047928500001944, "count": 2, "self": 0.21047928500001944 } } }, "_update_policy": { "total": 489.2460653079984, "count": 435, "self": 288.1082502690058, "children": { "TorchPPOOptimizer.update": { "total": 201.13781503899258, "count": 22857, "self": 201.13781503899258 } } } } } } }, "trainer_threads": { "total": 1.5069999790284783e-06, "count": 1, "self": 1.5069999790284783e-06 }, "TrainerController._save_models": { "total": 0.09691843799964772, "count": 1, "self": 0.0016929989997152006, "children": { "RLTrainer._checkpoint": { "total": 0.09522543899993252, "count": 1, "self": 0.09522543899993252 } } } } } } }