{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33100059628486633, "min": 0.33100059628486633, "max": 1.4590178728103638, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9908.833984375, "min": 9908.833984375, "max": 44260.765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989875.0, "min": 29952.0, "max": 989875.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989875.0, "min": 29952.0, "max": 989875.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6776401400566101, "min": -0.15186157822608948, "max": 0.6776401400566101, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 192.44979858398438, "min": -35.99119567871094, "max": 192.44979858398438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013824825175106525, "min": -0.051827091723680496, "max": 0.36007335782051086, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.926250457763672, "min": -13.371389389038086, "max": 85.33738708496094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06995065155785064, "min": 0.06299525146355985, "max": 0.07648114903534227, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.979309121809909, "min": 0.5155415998095374, "max": 1.0789698268830157, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016100394887150545, "min": 0.0008308326344738056, "max": 0.017251703971331675, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22540552842010764, "min": 0.009139158979211862, "max": 0.24152385559864345, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.481154649171429e-06, "min": 7.481154649171429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001047361650884, "min": 0.0001047361650884, "max": 0.0035083976305342007, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249368571428571, "min": 0.10249368571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349116, "min": 1.3886848, "max": 2.6175836000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025911920285714285, "min": 0.00025911920285714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036276688400000002, "min": 0.0036276688400000002, "max": 0.11696963342, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011113855056464672, "min": 0.011113855056464672, "max": 0.3657884895801544, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15559397637844086, "min": 0.15559397637844086, "max": 2.5605194568634033, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 274.9142857142857, "min": 274.0673076923077, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28866.0, "min": 15984.0, "max": 32938.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.725085694875036, "min": -1.0000000521540642, "max": 1.7259326793539982, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 181.13399796187878, "min": -29.93240164220333, "max": 188.00099823623896, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.725085694875036, "min": -1.0000000521540642, "max": 1.7259326793539982, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 181.13399796187878, "min": -29.93240164220333, "max": 188.00099823623896, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031949404245408784, "min": 0.031949404245408784, "max": 7.5791379464790225, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3546874457679223, "min": 3.3546874457679223, "max": 121.26620714366436, "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": "1745060211", "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": "1745063009" }, "total": 2798.6421242710003, "count": 1, "self": 0.6441146860001936, "children": { "run_training.setup": { "total": 0.03458353899998201, "count": 1, "self": 0.03458353899998201 }, "TrainerController.start_learning": { "total": 2797.963426046, "count": 1, "self": 1.8866308389815458, "children": { "TrainerController._reset_env": { "total": 3.6848245229999748, "count": 1, "self": 3.6848245229999748 }, "TrainerController.advance": { "total": 2792.2951193720187, "count": 64171, "self": 1.9078966550086989, "children": { "env_step": { "total": 1997.9872865529992, "count": 64171, "self": 1803.2775955500438, "children": { "SubprocessEnvManager._take_step": { "total": 193.6420893679549, "count": 64171, "self": 5.731440186035229, "children": { "TorchPolicy.evaluate": { "total": 187.91064918191967, "count": 62565, "self": 187.91064918191967 } } }, "workers": { "total": 1.0676016350004147, "count": 64171, "self": 0.0, "children": { "worker_root": { "total": 2791.5157128519736, "count": 64171, "is_parallel": true, "self": 1131.0723740120375, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0054208860000244385, "count": 1, "is_parallel": true, "self": 0.0035018510000099923, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019190350000144463, "count": 8, "is_parallel": true, "self": 0.0019190350000144463 } } }, "UnityEnvironment.step": { "total": 0.058890999999903215, "count": 1, "is_parallel": true, "self": 0.0007054739998011428, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00052554000001237, "count": 1, "is_parallel": true, "self": 0.00052554000001237 }, "communicator.exchange": { "total": 0.055574093000018365, "count": 1, "is_parallel": true, "self": 0.055574093000018365 }, "steps_from_proto": { "total": 0.002085893000071337, "count": 1, "is_parallel": true, "self": 0.000664689000245744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014212039998255932, "count": 8, "is_parallel": true, "self": 0.0014212039998255932 } } } } } } }, "UnityEnvironment.step": { "total": 1660.4433388399361, "count": 64170, "is_parallel": true, "self": 39.350366215013764, "children": { "UnityEnvironment._generate_step_input": { "total": 28.177122465998764, "count": 64170, "is_parallel": true, "self": 28.177122465998764 }, "communicator.exchange": { "total": 1473.252276495944, "count": 64170, "is_parallel": true, "self": 1473.252276495944 }, "steps_from_proto": { "total": 119.66357366297973, "count": 64170, "is_parallel": true, "self": 25.474332254884075, "children": { "_process_rank_one_or_two_observation": { "total": 94.18924140809565, "count": 513360, "is_parallel": true, "self": 94.18924140809565 } } } } } } } } } } }, "trainer_advance": { "total": 792.3999361640108, "count": 64171, "self": 3.505565256986074, "children": { "process_trajectory": { "total": 156.29021042801708, "count": 64171, "self": 155.9785987310171, "children": { "RLTrainer._checkpoint": { "total": 0.31161169699998936, "count": 2, "self": 0.31161169699998936 } } }, "_update_policy": { "total": 632.6041604790076, "count": 452, "self": 350.20712035001145, "children": { "TorchPPOOptimizer.update": { "total": 282.3970401289962, "count": 22797, "self": 282.3970401289962 } } } } } } }, "trainer_threads": { "total": 1.145000169344712e-06, "count": 1, "self": 1.145000169344712e-06 }, "TrainerController._save_models": { "total": 0.09685016699995685, "count": 1, "self": 0.001233321000199794, "children": { "RLTrainer._checkpoint": { "total": 0.09561684599975706, "count": 1, "self": 0.09561684599975706 } } } } } } }