{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3934801518917084, "min": 0.39156270027160645, "max": 1.3991166353225708, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11653.30859375, "min": 11653.30859375, "max": 42443.6015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989874.0, "min": 29952.0, "max": 989874.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989874.0, "min": 29952.0, "max": 989874.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4872932434082031, "min": -0.10621169954538345, "max": 0.5632720589637756, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 132.0564727783203, "min": -25.17217254638672, "max": 154.3365478515625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.002978281117975712, "min": -0.07607637345790863, "max": 0.3929622769355774, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.8071141839027405, "min": -20.46454429626465, "max": 94.70391082763672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06728147503634405, "min": 0.0648657434229534, "max": 0.07318615014522416, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9419406505088167, "min": 0.5123030510165691, "max": 1.0721503202221354, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014742131497076202, "min": 0.0010945898081160042, "max": 0.015876642882358283, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20638984095906682, "min": 0.015324257313624058, "max": 0.23814964323537424, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.295433282507139e-06, "min": 7.295433282507139e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010213606595509994, "min": 0.00010213606595509994, "max": 0.0036331789889403996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243177857142857, "min": 0.10243177857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340449, "min": 1.3886848, "max": 2.6110596000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025293467928571417, "min": 0.00025293467928571417, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003541085509999998, "min": 0.003541085509999998, "max": 0.12112485403999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012699590064585209, "min": 0.012699590064585209, "max": 0.631924569606781, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17779426276683807, "min": 0.17779426276683807, "max": 4.423471927642822, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 394.15584415584414, "min": 336.84090909090907, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30350.0, "min": 15984.0, "max": 33175.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4759246583108778, "min": -1.0000000521540642, "max": 1.6404204355891456, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.64619868993759, "min": -30.20100162923336, "max": 144.3569983318448, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4759246583108778, "min": -1.0000000521540642, "max": 1.6404204355891456, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.64619868993759, "min": -30.20100162923336, "max": 144.3569983318448, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.051344059006493935, "min": 0.051344059006493935, "max": 12.573345087468624, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.953492543500033, "min": 3.953492543500033, "max": 201.173521399498, "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": "1736210677", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736213293" }, "total": 2615.858218896, "count": 1, "self": 0.5929309100001774, "children": { "run_training.setup": { "total": 0.07350253200002044, "count": 1, "self": 0.07350253200002044 }, "TrainerController.start_learning": { "total": 2615.1917854539997, "count": 1, "self": 1.635096523993525, "children": { "TrainerController._reset_env": { "total": 2.4374365709998074, "count": 1, "self": 2.4374365709998074 }, "TrainerController.advance": { "total": 2611.0470743240066, "count": 63705, "self": 1.6331689311309674, "children": { "env_step": { "total": 1673.8676946729038, "count": 63705, "self": 1552.2880973898145, "children": { "SubprocessEnvManager._take_step": { "total": 120.61528319302238, "count": 63705, "self": 5.166436272989358, "children": { "TorchPolicy.evaluate": { "total": 115.44884692003302, "count": 62552, "self": 115.44884692003302 } } }, "workers": { "total": 0.9643140900668641, "count": 63705, "self": 0.0, "children": { "worker_root": { "total": 2609.831658891068, "count": 63705, "is_parallel": true, "self": 1191.160453600069, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026912619998711307, "count": 1, "is_parallel": true, "self": 0.0006866679998438485, "children": { "_process_rank_one_or_two_observation": { "total": 0.002004594000027282, "count": 8, "is_parallel": true, "self": 0.002004594000027282 } } }, "UnityEnvironment.step": { "total": 0.05391509700007191, "count": 1, "is_parallel": true, "self": 0.000756701000227622, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005060710000179824, "count": 1, "is_parallel": true, "self": 0.0005060710000179824 }, "communicator.exchange": { "total": 0.050533259999838265, "count": 1, "is_parallel": true, "self": 0.050533259999838265 }, "steps_from_proto": { "total": 0.0021190649999880407, "count": 1, "is_parallel": true, "self": 0.0004502290000800713, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016688359999079694, "count": 8, "is_parallel": true, "self": 0.0016688359999079694 } } } } } } }, "UnityEnvironment.step": { "total": 1418.6712052909988, "count": 63704, "is_parallel": true, "self": 39.077979528940205, "children": { "UnityEnvironment._generate_step_input": { "total": 28.790892771019116, "count": 63704, "is_parallel": true, "self": 28.790892771019116 }, "communicator.exchange": { "total": 1235.9065690339771, "count": 63704, "is_parallel": true, "self": 1235.9065690339771 }, "steps_from_proto": { "total": 114.8957639570624, "count": 63704, "is_parallel": true, "self": 24.191731259812286, "children": { "_process_rank_one_or_two_observation": { "total": 90.70403269725011, "count": 509632, "is_parallel": true, "self": 90.70403269725011 } } } } } } } } } } }, "trainer_advance": { "total": 935.5462107199717, "count": 63705, "self": 3.0064345949824656, "children": { "process_trajectory": { "total": 144.95343594099154, "count": 63705, "self": 144.77270160699186, "children": { "RLTrainer._checkpoint": { "total": 0.18073433399968053, "count": 2, "self": 0.18073433399968053 } } }, "_update_policy": { "total": 787.5863401839977, "count": 449, "self": 342.80076061201976, "children": { "TorchPPOOptimizer.update": { "total": 444.7855795719779, "count": 22833, "self": 444.7855795719779 } } } } } } }, "trainer_threads": { "total": 1.237999640579801e-06, "count": 1, "self": 1.237999640579801e-06 }, "TrainerController._save_models": { "total": 0.07217679699988366, "count": 1, "self": 0.0017260619997614413, "children": { "RLTrainer._checkpoint": { "total": 0.07045073500012222, "count": 1, "self": 0.07045073500012222 } } } } } } }