{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6191577911376953, "min": 0.5960368514060974, "max": 1.4565049409866333, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18574.734375, "min": 17776.203125, "max": 44184.53515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.23888228833675385, "min": -0.10210693627595901, "max": 0.25801268219947815, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 61.631629943847656, "min": -24.607770919799805, "max": 67.34130859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01471063494682312, "min": 0.007364691235125065, "max": 0.4073125123977661, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.7953438758850098, "min": 1.8411728143692017, "max": 96.53306579589844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06720328745238173, "min": 0.06621123698405515, "max": 0.07518984519369301, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0080493117857259, "min": 0.5157161376813035, "max": 1.0633909602343632, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01146255810696554, "min": 0.00038899416660733116, "max": 0.011730555315257296, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1719383716044831, "min": 0.0042789358326806425, "max": 0.1719383716044831, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.525897491399999e-06, "min": 7.525897491399999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011288846237099999, "min": 0.00011288846237099999, "max": 0.0032547656150782, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250860000000002, "min": 0.10250860000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376290000000004, "min": 1.3691136000000002, "max": 2.4012244, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026060913999999995, "min": 0.00026060913999999995, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039091371, "min": 0.0039091371, "max": 0.10851368782000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010335220955312252, "min": 0.010335220955312252, "max": 0.5094277858734131, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1550283133983612, "min": 0.14696715772151947, "max": 3.5659945011138916, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 553.3888888888889, "min": 519.1071428571429, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29883.0, "min": 15984.0, "max": 32354.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9649999781891152, "min": -1.0000000521540642, "max": 1.1236285440889853, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 52.10999882221222, "min": -32.000001668930054, "max": 62.92319846898317, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9649999781891152, "min": -1.0000000521540642, "max": 1.1236285440889853, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 52.10999882221222, "min": -32.000001668930054, "max": 62.92319846898317, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05982835197452611, "min": 0.0562631515992637, "max": 10.474536092951894, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.23073100662441, "min": 3.150736489558767, "max": 167.5925774872303, "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": "1742659477", "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 Training2 --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": "1742661705" }, "total": 2228.2977951800003, "count": 1, "self": 0.47587397000097553, "children": { "run_training.setup": { "total": 0.020603044999916165, "count": 1, "self": 0.020603044999916165 }, "TrainerController.start_learning": { "total": 2227.8013181649994, "count": 1, "self": 1.3502671778496733, "children": { "TrainerController._reset_env": { "total": 2.2035685930004547, "count": 1, "self": 2.2035685930004547 }, "TrainerController.advance": { "total": 2224.1551487851493, "count": 63348, "self": 1.4317077412479193, "children": { "env_step": { "total": 1524.682743356093, "count": 63348, "self": 1365.4318131149685, "children": { "SubprocessEnvManager._take_step": { "total": 158.45955560809944, "count": 63348, "self": 4.8267026960520525, "children": { "TorchPolicy.evaluate": { "total": 153.63285291204738, "count": 62561, "self": 153.63285291204738 } } }, "workers": { "total": 0.7913746330250433, "count": 63348, "self": 0.0, "children": { "worker_root": { "total": 2222.7515655900925, "count": 63348, "is_parallel": true, "self": 971.494638998136, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022417099999074708, "count": 1, "is_parallel": true, "self": 0.0008140969994201441, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014276130004873266, "count": 8, "is_parallel": true, "self": 0.0014276130004873266 } } }, "UnityEnvironment.step": { "total": 0.05294805900030042, "count": 1, "is_parallel": true, "self": 0.0005487809994519921, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048387700007879175, "count": 1, "is_parallel": true, "self": 0.00048387700007879175 }, "communicator.exchange": { "total": 0.05008036000072025, "count": 1, "is_parallel": true, "self": 0.05008036000072025 }, "steps_from_proto": { "total": 0.0018350410000493866, "count": 1, "is_parallel": true, "self": 0.00037685700135625666, "children": { "_process_rank_one_or_two_observation": { "total": 0.00145818399869313, "count": 8, "is_parallel": true, "self": 0.00145818399869313 } } } } } } }, "UnityEnvironment.step": { "total": 1251.2569265919565, "count": 63347, "is_parallel": true, "self": 32.61673461894679, "children": { "UnityEnvironment._generate_step_input": { "total": 24.828428966197862, "count": 63347, "is_parallel": true, "self": 24.828428966197862 }, "communicator.exchange": { "total": 1093.671562924861, "count": 63347, "is_parallel": true, "self": 1093.671562924861 }, "steps_from_proto": { "total": 100.14020008195075, "count": 63347, "is_parallel": true, "self": 20.35938970456391, "children": { "_process_rank_one_or_two_observation": { "total": 79.78081037738684, "count": 506776, "is_parallel": true, "self": 79.78081037738684 } } } } } } } } } } }, "trainer_advance": { "total": 698.0406976878085, "count": 63348, "self": 2.5819116387256145, "children": { "process_trajectory": { "total": 132.9798358890721, "count": 63348, "self": 132.76577882507172, "children": { "RLTrainer._checkpoint": { "total": 0.2140570640003716, "count": 2, "self": 0.2140570640003716 } } }, "_update_policy": { "total": 562.4789501600108, "count": 437, "self": 308.2765062900053, "children": { "TorchPPOOptimizer.update": { "total": 254.20244387000548, "count": 22866, "self": 254.20244387000548 } } } } } } }, "trainer_threads": { "total": 8.09999619377777e-07, "count": 1, "self": 8.09999619377777e-07 }, "TrainerController._save_models": { "total": 0.09233279900035996, "count": 1, "self": 0.0014714310000272235, "children": { "RLTrainer._checkpoint": { "total": 0.09086136800033273, "count": 1, "self": 0.09086136800033273 } } } } } } }