{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3585016131401062, "min": 0.3585016131401062, "max": 1.4783803224563599, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10651.7998046875, "min": 10651.7998046875, "max": 44848.14453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989897.0, "min": 29952.0, "max": 989897.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.19241192936897278, "min": -0.0969201847910881, "max": 0.2348700761795044, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 48.29539489746094, "min": -23.45468521118164, "max": 60.361610412597656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010496854782104492, "min": -0.0038050073198974133, "max": 0.35403022170066833, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.6347105503082275, "min": -0.9512518048286438, "max": 84.96725463867188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06860337453480397, "min": 0.06589225637333541, "max": 0.07405643996372376, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0290506180220595, "min": 0.5061101009620985, "max": 1.0627600727117776, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010312712442343278, "min": 0.0007441640817176255, "max": 0.010464106992907906, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15469068663514918, "min": 0.009384652455469484, "max": 0.15469068663514918, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.498657500479997e-06, "min": 7.498657500479997e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011247986250719996, "min": 0.00011247986250719996, "max": 0.0035080793306402993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249952, "min": 0.10249952, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374927999999999, "min": 1.3691136000000002, "max": 2.5693597, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000259702048, "min": 0.000259702048, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00389553072, "min": 0.00389553072, "max": 0.11695903402999996, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016930092126131058, "min": 0.016930092126131058, "max": 0.5329852104187012, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.25395137071609497, "min": 0.23712965846061707, "max": 3.730896472930908, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 601.8260869565217, "min": 601.8260869565217, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27684.0, "min": 15984.0, "max": 33367.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9197782239188319, "min": -1.0000000521540642, "max": 0.9197782239188319, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 42.309798300266266, "min": -32.000001668930054, "max": 42.814598478376865, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9197782239188319, "min": -1.0000000521540642, "max": 0.9197782239188319, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 42.309798300266266, "min": -32.000001668930054, "max": 42.814598478376865, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10576603296415313, "min": 0.10576603296415313, "max": 10.523467611521482, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.865237516351044, "min": 4.865237516351044, "max": 168.37548178434372, "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": "1699358282", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699360498" }, "total": 2216.006876726, "count": 1, "self": 0.4766246350000074, "children": { "run_training.setup": { "total": 0.04887384399989969, "count": 1, "self": 0.04887384399989969 }, "TrainerController.start_learning": { "total": 2215.481378247, "count": 1, "self": 1.4386498659696372, "children": { "TrainerController._reset_env": { "total": 3.5350714610001432, "count": 1, "self": 3.5350714610001432 }, "TrainerController.advance": { "total": 2210.4267567010306, "count": 63335, "self": 1.5220807149667053, "children": { "env_step": { "total": 1579.5943416139994, "count": 63335, "self": 1438.0310495749468, "children": { "SubprocessEnvManager._take_step": { "total": 140.65287873203965, "count": 63335, "self": 4.790681511102775, "children": { "TorchPolicy.evaluate": { "total": 135.86219722093688, "count": 62555, "self": 135.86219722093688 } } }, "workers": { "total": 0.9104133070129592, "count": 63335, "self": 0.0, "children": { "worker_root": { "total": 2210.653920895031, "count": 63335, "is_parallel": true, "self": 896.179684282994, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020100690001072508, "count": 1, "is_parallel": true, "self": 0.0006608420001157356, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013492269999915152, "count": 8, "is_parallel": true, "self": 0.0013492269999915152 } } }, "UnityEnvironment.step": { "total": 0.050171717000011995, "count": 1, "is_parallel": true, "self": 0.0005924409999806812, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004812669999409991, "count": 1, "is_parallel": true, "self": 0.0004812669999409991 }, "communicator.exchange": { "total": 0.04739393299996664, "count": 1, "is_parallel": true, "self": 0.04739393299996664 }, "steps_from_proto": { "total": 0.0017040760001236777, "count": 1, "is_parallel": true, "self": 0.0003707340006258164, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013333419994978613, "count": 8, "is_parallel": true, "self": 0.0013333419994978613 } } } } } } }, "UnityEnvironment.step": { "total": 1314.4742366120372, "count": 63334, "is_parallel": true, "self": 35.82643286203097, "children": { "UnityEnvironment._generate_step_input": { "total": 26.319977237994863, "count": 63334, "is_parallel": true, "self": 26.319977237994863 }, "communicator.exchange": { "total": 1147.301718756029, "count": 63334, "is_parallel": true, "self": 1147.301718756029 }, "steps_from_proto": { "total": 105.02610775598237, "count": 63334, "is_parallel": true, "self": 21.675202251128894, "children": { "_process_rank_one_or_two_observation": { "total": 83.35090550485347, "count": 506672, "is_parallel": true, "self": 83.35090550485347 } } } } } } } } } } }, "trainer_advance": { "total": 629.3103343720643, "count": 63335, "self": 2.8696329080969463, "children": { "process_trajectory": { "total": 125.6277221899652, "count": 63335, "self": 125.45913810396564, "children": { "RLTrainer._checkpoint": { "total": 0.1685840859995551, "count": 2, "self": 0.1685840859995551 } } }, "_update_policy": { "total": 500.81297927400215, "count": 446, "self": 295.74022419701464, "children": { "TorchPPOOptimizer.update": { "total": 205.0727550769875, "count": 22770, "self": 205.0727550769875 } } } } } } }, "trainer_threads": { "total": 1.0139997357327957e-06, "count": 1, "self": 1.0139997357327957e-06 }, "TrainerController._save_models": { "total": 0.08089920500015069, "count": 1, "self": 0.0013945210002930253, "children": { "RLTrainer._checkpoint": { "total": 0.07950468399985766, "count": 1, "self": 0.07950468399985766 } } } } } } }