{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.640616774559021, "min": 0.60373854637146, "max": 1.4937748908996582, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19116.00390625, "min": 18102.49609375, "max": 45315.15625, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29914.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29914.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.34423235058784485, "min": -0.23789487779140472, "max": 0.4009521007537842, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 90.8773422241211, "min": -56.618980407714844, "max": 106.65325927734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.5151433348655701, "min": -0.5151433348655701, "max": 0.20649656653404236, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -135.99783325195312, "min": -135.99783325195312, "max": 49.146183013916016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06558244162685395, "min": 0.06396150096114937, "max": 0.07302698495661507, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9181541827759553, "min": 0.5746175738893873, "max": 1.066220725835164, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.09474412143788954, "min": 0.00048811598062475345, "max": 0.09474412143788954, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.3264177001304536, "min": 0.006345507748121795, "max": 1.3264177001304536, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.536826059185716e-06, "min": 7.536826059185716e-06, "max": 0.00029476785174405, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010551556482860002, "min": 0.00010551556482860002, "max": 0.0036328531890489992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251224285714289, "min": 0.10251224285714289, "max": 0.19825595, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351714000000004, "min": 1.4351714000000004, "max": 2.610951000000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026097306142857155, "min": 0.00026097306142857155, "max": 0.009825769405, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036536228600000014, "min": 0.0036536228600000014, "max": 0.12111400490000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007593152578920126, "min": 0.007593152578920126, "max": 0.29148536920547485, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10630413889884949, "min": 0.10630413889884949, "max": 2.331882953643799, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 460.015873015873, "min": 442.26153846153846, "max": 998.1875, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28981.0, "min": 17224.0, "max": 33964.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.317679338157177, "min": -0.9366188028361648, "max": 1.4038399845361709, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 83.01379830390215, "min": -29.971801690757275, "max": 91.24959899485111, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.317679338157177, "min": -0.9366188028361648, "max": 1.4038399845361709, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 83.01379830390215, "min": -29.971801690757275, "max": 91.24959899485111, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.037159293860433595, "min": 0.0358496529108379, "max": 5.886541863282521, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3410355132073164, "min": 2.3302274392044637, "max": 105.95775353908539, "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": "1713840039", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713842194" }, "total": 2155.392921079, "count": 1, "self": 0.5386386129998755, "children": { "run_training.setup": { "total": 0.051535860000058165, "count": 1, "self": 0.051535860000058165 }, "TrainerController.start_learning": { "total": 2154.8027466060003, "count": 1, "self": 1.3871154969879171, "children": { "TrainerController._reset_env": { "total": 2.2068100569999842, "count": 1, "self": 2.2068100569999842 }, "TrainerController.advance": { "total": 2151.1239023060125, "count": 63514, "self": 1.429263774037281, "children": { "env_step": { "total": 1524.342439389003, "count": 63514, "self": 1391.9916999790019, "children": { "SubprocessEnvManager._take_step": { "total": 131.4946722379766, "count": 63514, "self": 4.679912526938779, "children": { "TorchPolicy.evaluate": { "total": 126.81475971103782, "count": 62579, "self": 126.81475971103782 } } }, "workers": { "total": 0.8560671720244954, "count": 63514, "self": 0.0, "children": { "worker_root": { "total": 2149.6791380870377, "count": 63514, "is_parallel": true, "self": 879.7806733169637, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00222984400011228, "count": 1, "is_parallel": true, "self": 0.000698827999713103, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015310160003991768, "count": 8, "is_parallel": true, "self": 0.0015310160003991768 } } }, "UnityEnvironment.step": { "total": 0.07136623700012024, "count": 1, "is_parallel": true, "self": 0.0006460390002303029, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040869999997994455, "count": 1, "is_parallel": true, "self": 0.00040869999997994455 }, "communicator.exchange": { "total": 0.0687425969999822, "count": 1, "is_parallel": true, "self": 0.0687425969999822 }, "steps_from_proto": { "total": 0.0015689009999277914, "count": 1, "is_parallel": true, "self": 0.00033440399988649006, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012344970000413014, "count": 8, "is_parallel": true, "self": 0.0012344970000413014 } } } } } } }, "UnityEnvironment.step": { "total": 1269.898464770074, "count": 63513, "is_parallel": true, "self": 34.965966277091184, "children": { "UnityEnvironment._generate_step_input": { "total": 23.607985612975426, "count": 63513, "is_parallel": true, "self": 23.607985612975426 }, "communicator.exchange": { "total": 1110.6239277740183, "count": 63513, "is_parallel": true, "self": 1110.6239277740183 }, "steps_from_proto": { "total": 100.70058510598915, "count": 63513, "is_parallel": true, "self": 20.446980659962264, "children": { "_process_rank_one_or_two_observation": { "total": 80.25360444602688, "count": 508104, "is_parallel": true, "self": 80.25360444602688 } } } } } } } } } } }, "trainer_advance": { "total": 625.3521991429723, "count": 63514, "self": 2.625361968918469, "children": { "process_trajectory": { "total": 127.05362057705565, "count": 63514, "self": 126.8456407660558, "children": { "RLTrainer._checkpoint": { "total": 0.20797981099985918, "count": 2, "self": 0.20797981099985918 } } }, "_update_policy": { "total": 495.67321659699815, "count": 455, "self": 289.971275103959, "children": { "TorchPPOOptimizer.update": { "total": 205.70194149303916, "count": 22818, "self": 205.70194149303916 } } } } } } }, "trainer_threads": { "total": 8.399997568631079e-07, "count": 1, "self": 8.399997568631079e-07 }, "TrainerController._save_models": { "total": 0.08491790600010063, "count": 1, "self": 0.0013946960002613196, "children": { "RLTrainer._checkpoint": { "total": 0.08352320999983931, "count": 1, "self": 0.08352320999983931 } } } } } } }