{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4227753281593323, "min": 0.4227753281593323, "max": 1.4035130739212036, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12662.966796875, "min": 12662.966796875, "max": 42576.97265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989935.0, "min": 29891.0, "max": 989935.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989935.0, "min": 29891.0, "max": 989935.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5472075343132019, "min": -0.08480988442897797, "max": 0.5472075343132019, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.38766479492188, "min": -20.43918228149414, "max": 149.38766479492188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.5827062129974365, "min": -0.5827062129974365, "max": 0.7334055304527283, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -159.07879638671875, "min": -159.07879638671875, "max": 173.81710815429688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06880309737295778, "min": 0.06303410240728963, "max": 0.07338600206421689, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9632433632214089, "min": 0.5121669554644687, "max": 1.1007900309632532, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.053455584703312665, "min": 0.0018368665227186263, "max": 0.053455584703312665, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.7483781858463773, "min": 0.022042398272623515, "max": 0.7483781858463773, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.547840341228574e-06, "min": 7.547840341228574e-06, "max": 0.0002952355301595857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010566976477720003, "min": 0.00010566976477720003, "max": 0.0036344419885193996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251591428571429, "min": 0.10251591428571429, "max": 0.19841184285714286, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352228, "min": 1.3888829, "max": 2.6114806000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026133983714285723, "min": 0.00026133983714285723, "max": 0.009841343101428571, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036587577200000014, "min": 0.0036587577200000014, "max": 0.12116691194, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013660682365298271, "min": 0.013217068277299404, "max": 0.6735454797744751, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1912495493888855, "min": 0.1850389540195465, "max": 4.714818477630615, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.07954545454544, "min": 349.4022988505747, "max": 983.1515151515151, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30895.0, "min": 16690.0, "max": 32444.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.557974978858097, "min": -0.8650588735061533, "max": 1.6218430201841305, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.10179813951254, "min": -28.474001720547676, "max": 137.10179813951254, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.557974978858097, "min": -0.8650588735061533, "max": 1.6218430201841305, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.10179813951254, "min": -28.474001720547676, "max": 137.10179813951254, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04995945484221342, "min": 0.04917197070064876, "max": 13.278092069660916, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.3964320261147805, "min": 3.935927780577913, "max": 225.72756518423557, "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": "1756135625", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/home/ubuntu/.local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756136428" }, "total": 802.8712916290001, "count": 1, "self": 0.2177329070000269, "children": { "run_training.setup": { "total": 0.01570750200016846, "count": 1, "self": 0.01570750200016846 }, "TrainerController.start_learning": { "total": 802.6378512199999, "count": 1, "self": 0.6336360961258833, "children": { "TrainerController._reset_env": { "total": 1.1959457339999062, "count": 1, "self": 1.1959457339999062 }, "TrainerController.advance": { "total": 800.7609756408747, "count": 63862, "self": 0.5845655628495479, "children": { "env_step": { "total": 501.1566706939698, "count": 63862, "self": 435.2795409839355, "children": { "SubprocessEnvManager._take_step": { "total": 65.46808117204228, "count": 63862, "self": 2.05530309798678, "children": { "TorchPolicy.evaluate": { "total": 63.412778074055495, "count": 62550, "self": 63.412778074055495 } } }, "workers": { "total": 0.409048537992021, "count": 63862, "self": 0.0, "children": { "worker_root": { "total": 801.4139665399616, "count": 63862, "is_parallel": true, "self": 410.96247375195344, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011772079997172114, "count": 1, "is_parallel": true, "self": 0.0003702619983414479, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008069460013757634, "count": 8, "is_parallel": true, "self": 0.0008069460013757634 } } }, "UnityEnvironment.step": { "total": 0.017153541999959998, "count": 1, "is_parallel": true, "self": 0.00016109099988170783, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001901410000755277, "count": 1, "is_parallel": true, "self": 0.0001901410000755277 }, "communicator.exchange": { "total": 0.016252166999947804, "count": 1, "is_parallel": true, "self": 0.016252166999947804 }, "steps_from_proto": { "total": 0.000550143000054959, "count": 1, "is_parallel": true, "self": 0.00012821100062865298, "children": { "_process_rank_one_or_two_observation": { "total": 0.000421931999426306, "count": 8, "is_parallel": true, "self": 0.000421931999426306 } } } } } } }, "UnityEnvironment.step": { "total": 390.4514927880082, "count": 63861, "is_parallel": true, "self": 9.907689546058464, "children": { "UnityEnvironment._generate_step_input": { "total": 6.942700701885769, "count": 63861, "is_parallel": true, "self": 6.942700701885769 }, "communicator.exchange": { "total": 344.84160323801643, "count": 63861, "is_parallel": true, "self": 344.84160323801643 }, "steps_from_proto": { "total": 28.759499302047516, "count": 63861, "is_parallel": true, "self": 5.987972682886721, "children": { "_process_rank_one_or_two_observation": { "total": 22.771526619160795, "count": 510888, "is_parallel": true, "self": 22.771526619160795 } } } } } } } } } } }, "trainer_advance": { "total": 299.01973938405536, "count": 63862, "self": 1.283134781041099, "children": { "process_trajectory": { "total": 58.892194951010424, "count": 63862, "self": 58.78063713501024, "children": { "RLTrainer._checkpoint": { "total": 0.111557816000186, "count": 2, "self": 0.111557816000186 } } }, "_update_policy": { "total": 238.84440965200383, "count": 458, "self": 138.19577779496603, "children": { "TorchPPOOptimizer.update": { "total": 100.6486318570378, "count": 22794, "self": 100.6486318570378 } } } } } } }, "trainer_threads": { "total": 6.199998097144999e-07, "count": 1, "self": 6.199998097144999e-07 }, "TrainerController._save_models": { "total": 0.04729312899962679, "count": 1, "self": 0.0013493499996002356, "children": { "RLTrainer._checkpoint": { "total": 0.04594377900002655, "count": 1, "self": 0.04594377900002655 } } } } } } }