{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45940449833869934, "min": 0.452622652053833, "max": 1.4541568756103516, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13782.134765625, "min": 13593.1630859375, "max": 44113.3046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5135005116462708, "min": -0.10080506652593613, "max": 0.5340887904167175, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.29364013671875, "min": -24.294021606445312, "max": 150.07894897460938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06755489110946655, "min": -0.001537912292405963, "max": 0.3764190077781677, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 18.982925415039062, "min": -0.4075467586517334, "max": 89.2113037109375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06781496218588602, "min": 0.06528137805287401, "max": 0.07279365603964975, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9494094706024042, "min": 0.5007196971945914, "max": 1.0641457588627576, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017881482677189867, "min": 0.001409126147457493, "max": 0.017881482677189867, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25034075748065815, "min": 0.01577675011701727, "max": 0.25034075748065815, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.570618905064284e-06, "min": 7.570618905064284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010598866467089997, "min": 0.00010598866467089997, "max": 0.0035059508313498, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252350714285716, "min": 0.10252350714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353291000000001, "min": 1.3886848, "max": 2.5686502000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002620983635714285, "min": 0.0002620983635714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003669377089999999, "min": 0.003669377089999999, "max": 0.11688815498000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012144171632826328, "min": 0.012144171632826328, "max": 0.5424908399581909, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17001840472221375, "min": 0.17001840472221375, "max": 3.797435760498047, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 360.3863636363636, "min": 360.3863636363636, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31714.0, "min": 15984.0, "max": 32956.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5941545260562138, "min": -1.0000000521540642, "max": 1.6372891404183514, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 140.28559829294682, "min": -29.80200169235468, "max": 140.28559829294682, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5941545260562138, "min": -1.0000000521540642, "max": 1.6372891404183514, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 140.28559829294682, "min": -29.80200169235468, "max": 140.28559829294682, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0451181937870305, "min": 0.0451181937870305, "max": 10.89273776859045, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9704010532586835, "min": 3.737478357972577, "max": 174.2838042974472, "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": "1749400793", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749403134" }, "total": 2341.151412698, "count": 1, "self": 0.6931569239995952, "children": { "run_training.setup": { "total": 0.020169152000107715, "count": 1, "self": 0.020169152000107715 }, "TrainerController.start_learning": { "total": 2340.4380866220004, "count": 1, "self": 1.621817987004306, "children": { "TrainerController._reset_env": { "total": 2.9492849969999497, "count": 1, "self": 2.9492849969999497 }, "TrainerController.advance": { "total": 2335.735750944996, "count": 63749, "self": 1.6203059689473776, "children": { "env_step": { "total": 1639.885992155062, "count": 63749, "self": 1468.762386415095, "children": { "SubprocessEnvManager._take_step": { "total": 170.18711028695338, "count": 63749, "self": 5.03023862597388, "children": { "TorchPolicy.evaluate": { "total": 165.1568716609795, "count": 62581, "self": 165.1568716609795 } } }, "workers": { "total": 0.9364954530135492, "count": 63749, "self": 0.0, "children": { "worker_root": { "total": 2334.437154742976, "count": 63749, "is_parallel": true, "self": 990.7913496230208, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023934180001106142, "count": 1, "is_parallel": true, "self": 0.0007107130006716034, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016827049994390109, "count": 8, "is_parallel": true, "self": 0.0016827049994390109 } } }, "UnityEnvironment.step": { "total": 0.0866910629999893, "count": 1, "is_parallel": true, "self": 0.0006148170000415121, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005298139999467821, "count": 1, "is_parallel": true, "self": 0.0005298139999467821 }, "communicator.exchange": { "total": 0.08046294099995066, "count": 1, "is_parallel": true, "self": 0.08046294099995066 }, "steps_from_proto": { "total": 0.005083491000050344, "count": 1, "is_parallel": true, "self": 0.0024773179998192063, "children": { "_process_rank_one_or_two_observation": { "total": 0.002606173000231138, "count": 8, "is_parallel": true, "self": 0.002606173000231138 } } } } } } }, "UnityEnvironment.step": { "total": 1343.6458051199552, "count": 63748, "is_parallel": true, "self": 33.239451888040776, "children": { "UnityEnvironment._generate_step_input": { "total": 24.051352115944837, "count": 63748, "is_parallel": true, "self": 24.051352115944837 }, "communicator.exchange": { "total": 1184.0108788790765, "count": 63748, "is_parallel": true, "self": 1184.0108788790765 }, "steps_from_proto": { "total": 102.3441222368931, "count": 63748, "is_parallel": true, "self": 21.141056987793718, "children": { "_process_rank_one_or_two_observation": { "total": 81.20306524909938, "count": 509984, "is_parallel": true, "self": 81.20306524909938 } } } } } } } } } } }, "trainer_advance": { "total": 694.2294528209866, "count": 63749, "self": 3.1552955390891384, "children": { "process_trajectory": { "total": 135.96707084789796, "count": 63749, "self": 135.71415270089756, "children": { "RLTrainer._checkpoint": { "total": 0.2529181470004005, "count": 2, "self": 0.2529181470004005 } } }, "_update_policy": { "total": 555.1070864339995, "count": 452, "self": 307.73894934208806, "children": { "TorchPPOOptimizer.update": { "total": 247.36813709191142, "count": 22836, "self": 247.36813709191142 } } } } } } }, "trainer_threads": { "total": 1.3480002962751314e-06, "count": 1, "self": 1.3480002962751314e-06 }, "TrainerController._save_models": { "total": 0.1312313449998328, "count": 1, "self": 0.0016701869999451446, "children": { "RLTrainer._checkpoint": { "total": 0.12956115799988766, "count": 1, "self": 0.12956115799988766 } } } } } } }