{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.482425719499588, "min": 0.4800167977809906, "max": 1.4426230192184448, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14750.6484375, "min": 14423.544921875, "max": 43763.41015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4827583432197571, "min": -0.08610346168279648, "max": 0.5138460993766785, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.79302978515625, "min": -20.664831161499023, "max": 143.36306762695312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015672221779823303, "min": -0.0035532887559384108, "max": 0.2822442352771759, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.27851676940918, "min": -0.8883221745491028, "max": 67.73861694335938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06795970206329904, "min": 0.06590084451500186, "max": 0.07468137035067442, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9514358288861866, "min": 0.49225976553360196, "max": 1.054969938603166, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012666516635658742, "min": 0.0002162637314892551, "max": 0.01412053057685539, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1773312328992224, "min": 0.0028114285093603164, "max": 0.19768742807597547, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.25304758235e-06, "min": 7.25304758235e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001015426661529, "min": 0.0001015426661529, "max": 0.0036324355891882, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241765, "min": 0.10241765, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338471, "min": 1.3886848, "max": 2.610811800000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000251523235, "min": 0.000251523235, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035213252899999998, "min": 0.0035213252899999998, "max": 0.12110009881999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011739284731447697, "min": 0.011739284731447697, "max": 0.5053572058677673, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1643499881029129, "min": 0.1643499881029129, "max": 3.5375006198883057, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 396.90277777777777, "min": 379.38666666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28577.0, "min": 15984.0, "max": 32595.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5197388647745054, "min": -1.0000000521540642, "max": 1.5392666456324082, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 109.42119826376438, "min": -31.998401671648026, "max": 124.68059829622507, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5197388647745054, "min": -1.0000000521540642, "max": 1.5392666456324082, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 109.42119826376438, "min": -31.998401671648026, "max": 124.68059829622507, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04847686697272972, "min": 0.04847686697272972, "max": 10.231782138813287, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4903344220365398, "min": 3.4903344220365398, "max": 163.7085142210126, "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": "1702455990", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702458290" }, "total": 2299.96404809, "count": 1, "self": 0.47504725099997813, "children": { "run_training.setup": { "total": 0.05977205499993943, "count": 1, "self": 0.05977205499993943 }, "TrainerController.start_learning": { "total": 2299.429228784, "count": 1, "self": 1.4515928999771859, "children": { "TrainerController._reset_env": { "total": 3.0332781939998767, "count": 1, "self": 3.0332781939998767 }, "TrainerController.advance": { "total": 2294.866821593023, "count": 63604, "self": 1.5245517741077492, "children": { "env_step": { "total": 1655.581188976926, "count": 63604, "self": 1517.1464505548943, "children": { "SubprocessEnvManager._take_step": { "total": 137.48567706798235, "count": 63604, "self": 5.000927856892304, "children": { "TorchPolicy.evaluate": { "total": 132.48474921109005, "count": 62551, "self": 132.48474921109005 } } }, "workers": { "total": 0.9490613540492632, "count": 63604, "self": 0.0, "children": { "worker_root": { "total": 2294.450355410899, "count": 63604, "is_parallel": true, "self": 904.5040759559363, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021297270000104618, "count": 1, "is_parallel": true, "self": 0.0007250720002502931, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014046549997601687, "count": 8, "is_parallel": true, "self": 0.0014046549997601687 } } }, "UnityEnvironment.step": { "total": 0.09860153400018135, "count": 1, "is_parallel": true, "self": 0.00063131400020211, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045146200000090175, "count": 1, "is_parallel": true, "self": 0.00045146200000090175 }, "communicator.exchange": { "total": 0.09584250400007477, "count": 1, "is_parallel": true, "self": 0.09584250400007477 }, "steps_from_proto": { "total": 0.0016762539999035653, "count": 1, "is_parallel": true, "self": 0.00036427999975785497, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013119740001457103, "count": 8, "is_parallel": true, "self": 0.0013119740001457103 } } } } } } }, "UnityEnvironment.step": { "total": 1389.946279454963, "count": 63603, "is_parallel": true, "self": 34.94857073182038, "children": { "UnityEnvironment._generate_step_input": { "total": 26.021146145101966, "count": 63603, "is_parallel": true, "self": 26.021146145101966 }, "communicator.exchange": { "total": 1223.9252890740433, "count": 63603, "is_parallel": true, "self": 1223.9252890740433 }, "steps_from_proto": { "total": 105.05127350399721, "count": 63603, "is_parallel": true, "self": 21.505037962904453, "children": { "_process_rank_one_or_two_observation": { "total": 83.54623554109276, "count": 508824, "is_parallel": true, "self": 83.54623554109276 } } } } } } } } } } }, "trainer_advance": { "total": 637.7610808419895, "count": 63604, "self": 2.881154961075026, "children": { "process_trajectory": { "total": 130.1372171069156, "count": 63604, "self": 129.9676417849164, "children": { "RLTrainer._checkpoint": { "total": 0.16957532199921843, "count": 2, "self": 0.16957532199921843 } } }, "_update_policy": { "total": 504.74270877399886, "count": 453, "self": 301.9607900600463, "children": { "TorchPPOOptimizer.update": { "total": 202.78191871395256, "count": 22749, "self": 202.78191871395256 } } } } } } }, "trainer_threads": { "total": 1.0699995982577093e-06, "count": 1, "self": 1.0699995982577093e-06 }, "TrainerController._save_models": { "total": 0.07753502700052195, "count": 1, "self": 0.0011830980010927306, "children": { "RLTrainer._checkpoint": { "total": 0.07635192899942922, "count": 1, "self": 0.07635192899942922 } } } } } } }