{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30174532532691956, "min": 0.30111098289489746, "max": 1.4569752216339111, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9177.8857421875, "min": 8893.6142578125, "max": 44198.80078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.485789030790329, "min": -0.11082945764064789, "max": 0.5344838500022888, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 133.59197998046875, "min": -26.70989990234375, "max": 144.31063842773438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06109166890382767, "min": -0.016629774123430252, "max": 0.3125622868537903, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.800209045410156, "min": -4.523298740386963, "max": 75.3275146484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07247156131192807, "min": 0.0639174328909056, "max": 0.07273752634566755, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.014601858366993, "min": 0.48495898766047724, "max": 1.0463508848333731, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01701817784322418, "min": 0.0007437264070160322, "max": 0.01701817784322418, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23825448980513853, "min": 0.008924716884192387, "max": 0.23825448980513853, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.333490412678569e-06, "min": 7.333490412678569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010266886577749996, "min": 0.00010266886577749996, "max": 0.0032589569136811, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244446428571428, "min": 0.10244446428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342225, "min": 1.3886848, "max": 2.3863189, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002542019821428571, "min": 0.0002542019821428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003558827749999999, "min": 0.003558827749999999, "max": 0.10865325811000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011915902607142925, "min": 0.011915902607142925, "max": 0.41923269629478455, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1668226420879364, "min": 0.1668226420879364, "max": 2.934628963470459, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 394.9875, "min": 361.58620689655174, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31599.0, "min": 15984.0, "max": 33810.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4299374838359653, "min": -1.0000000521540642, "max": 1.5665973110993703, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.39499870687723, "min": -30.604801654815674, "max": 134.53999774158, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4299374838359653, "min": -1.0000000521540642, "max": 1.5665973110993703, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.39499870687723, "min": -30.604801654815674, "max": 134.53999774158, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04875061192142312, "min": 0.04630890977928231, "max": 8.244974036701024, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.900048953713849, "min": 3.662518389726756, "max": 131.91958458721638, "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": "1739874870", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739877141" }, "total": 2270.917346591, "count": 1, "self": 0.5317507879994992, "children": { "run_training.setup": { "total": 0.020596433999799046, "count": 1, "self": 0.020596433999799046 }, "TrainerController.start_learning": { "total": 2270.3649993690005, "count": 1, "self": 1.4216132280434977, "children": { "TrainerController._reset_env": { "total": 2.1535198769997805, "count": 1, "self": 2.1535198769997805 }, "TrainerController.advance": { "total": 2266.697146882958, "count": 63715, "self": 1.4656953820572198, "children": { "env_step": { "total": 1584.6988095608945, "count": 63715, "self": 1424.0284235659528, "children": { "SubprocessEnvManager._take_step": { "total": 159.81959405201223, "count": 63715, "self": 4.82011118288392, "children": { "TorchPolicy.evaluate": { "total": 154.99948286912831, "count": 62558, "self": 154.99948286912831 } } }, "workers": { "total": 0.8507919429293906, "count": 63715, "self": 0.0, "children": { "worker_root": { "total": 2265.141849779913, "count": 63715, "is_parallel": true, "self": 957.9124650790386, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021050399996056512, "count": 1, "is_parallel": true, "self": 0.0007095929986462579, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013954470009593933, "count": 8, "is_parallel": true, "self": 0.0013954470009593933 } } }, "UnityEnvironment.step": { "total": 0.04745150000007925, "count": 1, "is_parallel": true, "self": 0.0005292370005918201, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004973239997525525, "count": 1, "is_parallel": true, "self": 0.0004973239997525525 }, "communicator.exchange": { "total": 0.04471848499997577, "count": 1, "is_parallel": true, "self": 0.04471848499997577 }, "steps_from_proto": { "total": 0.0017064539997591055, "count": 1, "is_parallel": true, "self": 0.00037717499890277395, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013292790008563315, "count": 8, "is_parallel": true, "self": 0.0013292790008563315 } } } } } } }, "UnityEnvironment.step": { "total": 1307.2293847008746, "count": 63714, "is_parallel": true, "self": 32.143628979924415, "children": { "UnityEnvironment._generate_step_input": { "total": 24.11649713707584, "count": 63714, "is_parallel": true, "self": 24.11649713707584 }, "communicator.exchange": { "total": 1150.885577916907, "count": 63714, "is_parallel": true, "self": 1150.885577916907 }, "steps_from_proto": { "total": 100.08368066696721, "count": 63714, "is_parallel": true, "self": 20.654079620931498, "children": { "_process_rank_one_or_two_observation": { "total": 79.42960104603571, "count": 509712, "is_parallel": true, "self": 79.42960104603571 } } } } } } } } } } }, "trainer_advance": { "total": 680.5326419400062, "count": 63715, "self": 2.6487831570852904, "children": { "process_trajectory": { "total": 130.1719660099343, "count": 63715, "self": 129.91227057293418, "children": { "RLTrainer._checkpoint": { "total": 0.25969543700011855, "count": 2, "self": 0.25969543700011855 } } }, "_update_policy": { "total": 547.7118927729866, "count": 444, "self": 300.1547657120068, "children": { "TorchPPOOptimizer.update": { "total": 247.55712706097984, "count": 22833, "self": 247.55712706097984 } } } } } } }, "trainer_threads": { "total": 9.28000190469902e-07, "count": 1, "self": 9.28000190469902e-07 }, "TrainerController._save_models": { "total": 0.09271845299917914, "count": 1, "self": 0.0014304439991974505, "children": { "RLTrainer._checkpoint": { "total": 0.09128800899998168, "count": 1, "self": 0.09128800899998168 } } } } } } }