{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.581639289855957, "min": 0.581639289855957, "max": 1.479786992073059, "count": 23 }, "Pyramids.Policy.Entropy.sum": { "value": 17514.322265625, "min": 17514.322265625, "max": 44890.81640625, "count": 23 }, "Pyramids.Step.mean": { "value": 689987.0, "min": 29949.0, "max": 689987.0, "count": 23 }, "Pyramids.Step.sum": { "value": 689987.0, "min": 29949.0, "max": 689987.0, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4100797772407532, "min": -0.10319365561008453, "max": 0.5421781539916992, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.72154235839844, "min": -24.869670867919922, "max": 150.72552490234375, "count": 23 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03461519628763199, "min": -0.03781283274292946, "max": 0.18148073554039001, "count": 23 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -9.346102714538574, "min": -9.944774627685547, "max": 43.55537796020508, "count": 23 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0699199747916591, "min": 0.06555061213477777, "max": 0.07482921541429222, "count": 23 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0487996218748865, "min": 0.5037953882302886, "max": 1.0732446086864607, "count": 23 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01549572353061057, "min": 0.0008243943862807425, "max": 0.015516341606667658, "count": 23 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23243585295915856, "min": 0.011040837830371663, "max": 0.23243585295915856, "count": 23 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002325041358319622, "min": 0.0002325041358319622, "max": 0.0002984110148153762, "count": 23 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0034875620374794332, "min": 0.0020888771037076335, "max": 0.0039690918769694, "count": 23 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.17750137111111114, "min": 0.17750137111111114, "max": 0.1994703380952381, "count": 23 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.662520566666667, "min": 1.3962923666666667, "max": 2.7825234000000005, "count": 23 }, "Pyramids.Policy.Beta.mean": { "value": 0.0077523869740000004, "min": 0.0077523869740000004, "max": 0.009947086775714284, "count": 23 }, "Pyramids.Policy.Beta.sum": { "value": 0.11628580461, "min": 0.06962960742999999, "max": 0.13231075694, "count": 23 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009772066958248615, "min": 0.009772066958248615, "max": 0.362361878156662, "count": 23 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1465810090303421, "min": 0.1465810090303421, "max": 2.5365331172943115, "count": 23 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 382.65432098765433, "min": 346.29761904761904, "max": 999.0, "count": 23 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30995.0, "min": 16748.0, "max": 31942.0, "count": 23 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.444459236882351, "min": -0.9999613425424022, "max": 1.582257120559613, "count": 23 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 117.00119818747044, "min": -30.99880161881447, "max": 132.90959812700748, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.444459236882351, "min": -0.9999613425424022, "max": 1.582257120559613, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 117.00119818747044, "min": -30.99880161881447, "max": 132.90959812700748, "count": 23 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03912377686176541, "min": 0.03912377686176541, "max": 7.160313461633289, "count": 23 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1690259258029982, "min": 3.1690259258029982, "max": 121.72532884776592, "count": 23 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1785244323", "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 Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785245977" }, "total": 1653.895400755, "count": 1, "self": 1.0976364769994689, "children": { "run_training.setup": { "total": 0.024827982000260818, "count": 1, "self": 0.024827982000260818 }, "TrainerController.start_learning": { "total": 1652.7729362960004, "count": 1, "self": 1.0470914650409213, "children": { "TrainerController._reset_env": { "total": 2.1505137209996974, "count": 1, "self": 2.1505137209996974 }, "TrainerController.advance": { "total": 1649.4030763189594, "count": 44970, "self": 1.0889252299703003, "children": { "env_step": { "total": 1188.9054217689131, "count": 44970, "self": 1074.2522155431097, "children": { "SubprocessEnvManager._take_step": { "total": 114.02003679693144, "count": 44970, "self": 3.676718969021749, "children": { "TorchPolicy.evaluate": { "total": 110.34331782790969, "count": 44227, "self": 110.34331782790969 } } }, "workers": { "total": 0.6331694288719518, "count": 44969, "self": 0.0, "children": { "worker_root": { "total": 1648.5552025630077, "count": 44969, "is_parallel": true, "self": 663.1849250009795, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017631600003369385, "count": 1, "is_parallel": true, "self": 0.0005508030017153942, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012123569986215443, "count": 8, "is_parallel": true, "self": 0.0012123569986215443 } } }, "UnityEnvironment.step": { "total": 0.053428233999966324, "count": 1, "is_parallel": true, "self": 0.0005470029996104131, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000523206000252685, "count": 1, "is_parallel": true, "self": 0.000523206000252685 }, "communicator.exchange": { "total": 0.05044963899990762, "count": 1, "is_parallel": true, "self": 0.05044963899990762 }, "steps_from_proto": { "total": 0.0019083860001956054, "count": 1, "is_parallel": true, "self": 0.0003943830001844617, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015140030000111437, "count": 8, "is_parallel": true, "self": 0.0015140030000111437 } } } } } } }, "UnityEnvironment.step": { "total": 985.3702775620281, "count": 44968, "is_parallel": true, "self": 24.79837207494893, "children": { "UnityEnvironment._generate_step_input": { "total": 17.150668508954823, "count": 44968, "is_parallel": true, "self": 17.150668508954823 }, "communicator.exchange": { "total": 863.6788897590568, "count": 44968, "is_parallel": true, "self": 863.6788897590568 }, "steps_from_proto": { "total": 79.7423472190676, "count": 44968, "is_parallel": true, "self": 16.82470672211457, "children": { "_process_rank_one_or_two_observation": { "total": 62.91764049695303, "count": 359744, "is_parallel": true, "self": 62.91764049695303 } } } } } } } } } } }, "trainer_advance": { "total": 459.40872932007596, "count": 44969, "self": 1.9739385971197407, "children": { "process_trajectory": { "total": 81.38887008595748, "count": 44969, "self": 81.27674894195707, "children": { "RLTrainer._checkpoint": { "total": 0.11212114400041173, "count": 1, "self": 0.11212114400041173 } } }, "_update_policy": { "total": 376.04592063699874, "count": 315, "self": 204.00977746501576, "children": { "TorchPPOOptimizer.update": { "total": 172.03614317198299, "count": 16140, "self": 172.03614317198299 } } } } } } }, "trainer_threads": { "total": 1.9030003386433236e-06, "count": 1, "self": 1.9030003386433236e-06 }, "TrainerController._save_models": { "total": 0.1722528880000027, "count": 1, "self": 0.003753159999178024, "children": { "RLTrainer._checkpoint": { "total": 0.1684997280008247, "count": 1, "self": 0.1684997280008247 } } } } } } }