{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5117917656898499, "min": 0.49852800369262695, "max": 1.471538782119751, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15476.5830078125, "min": 14947.86328125, "max": 44640.6015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1199384406208992, "min": -0.11409170180559158, "max": 0.2255753129720688, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 29.86467170715332, "min": -27.610191345214844, "max": 57.2961311340332, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010806557722389698, "min": 0.0060212574899196625, "max": 0.4488334357738495, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.6908328533172607, "min": 1.5293993949890137, "max": 106.37352752685547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06551359204292698, "min": 0.06409629389604221, "max": 0.07269348186059182, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9171902886009776, "min": 0.4967244300673831, "max": 1.0904022279088774, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005360458122811993, "min": 0.00020682080511139506, "max": 0.008212921173729964, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07504641371936789, "min": 0.002688670466448136, "max": 0.1149808964322195, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.723190282778573e-06, "min": 7.723190282778573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010812466395890004, "min": 0.00010812466395890004, "max": 0.0035083685305438996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257436428571429, "min": 0.10257436428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360411, "min": 1.3886848, "max": 2.5694561000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026717899214285726, "min": 0.00026717899214285726, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003740505890000002, "min": 0.003740505890000002, "max": 0.11696866439, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013316773809492588, "min": 0.013316773809492588, "max": 0.4380190670490265, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18643483519554138, "min": 0.18643483519554138, "max": 3.066133499145508, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 723.3636363636364, "min": 665.4347826086956, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31828.0, "min": 15984.0, "max": 32774.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.3217863320288333, "min": -1.0000000521540642, "max": 0.72570431119074, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 14.158598609268665, "min": -31.994001656770706, "max": 33.382398314774036, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.3217863320288333, "min": -1.0000000521540642, "max": 0.72570431119074, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 14.158598609268665, "min": -31.994001656770706, "max": 33.382398314774036, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10175450589634817, "min": 0.09852509213479883, "max": 9.469482328742743, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.477198259439319, "min": 3.989068800583482, "max": 151.51171725988388, "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": "1736747372", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [GCC 11.2.0]", "command_line_arguments": "/home/alex/.conda/envs/hf_ml_agent/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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1736748439" }, "total": 1067.6023671079893, "count": 1, "self": 0.2189692779793404, "children": { "run_training.setup": { "total": 0.012241890013683587, "count": 1, "self": 0.012241890013683587 }, "TrainerController.start_learning": { "total": 1067.3711559399962, "count": 1, "self": 1.0347648920724168, "children": { "TrainerController._reset_env": { "total": 1.1975730559788644, "count": 1, "self": 1.1975730559788644 }, "TrainerController.advance": { "total": 1065.083307217923, "count": 63298, "self": 0.9398801948700566, "children": { "env_step": { "total": 682.5344668177422, "count": 63298, "self": 618.9120155200944, "children": { "SubprocessEnvManager._take_step": { "total": 62.96244089011452, "count": 63298, "self": 2.5651276356365997, "children": { "TorchPolicy.evaluate": { "total": 60.39731325447792, "count": 62570, "self": 60.39731325447792 } } }, "workers": { "total": 0.6600104075332638, "count": 63298, "self": 0.0, "children": { "worker_root": { "total": 1065.933869417844, "count": 63298, "is_parallel": true, "self": 515.0397839322395, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010309729841537774, "count": 1, "is_parallel": true, "self": 0.0003035239933524281, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007274489908013493, "count": 8, "is_parallel": true, "self": 0.0007274489908013493 } } }, "UnityEnvironment.step": { "total": 0.022479076025774702, "count": 1, "is_parallel": true, "self": 0.00019428404630161822, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018611500854603946, "count": 1, "is_parallel": true, "self": 0.00018611500854603946 }, "communicator.exchange": { "total": 0.02147064797463827, "count": 1, "is_parallel": true, "self": 0.02147064797463827 }, "steps_from_proto": { "total": 0.0006280289962887764, "count": 1, "is_parallel": true, "self": 0.00015540700405836105, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047262199223041534, "count": 8, "is_parallel": true, "self": 0.00047262199223041534 } } } } } } }, "UnityEnvironment.step": { "total": 550.8940854856046, "count": 63297, "is_parallel": true, "self": 17.659048755216645, "children": { "UnityEnvironment._generate_step_input": { "total": 10.517932977789314, "count": 63297, "is_parallel": true, "self": 10.517932977789314 }, "communicator.exchange": { "total": 474.7157054791751, "count": 63297, "is_parallel": true, "self": 474.7157054791751 }, "steps_from_proto": { "total": 48.00139827342355, "count": 63297, "is_parallel": true, "self": 10.377697081217775, "children": { "_process_rank_one_or_two_observation": { "total": 37.62370119220577, "count": 506376, "is_parallel": true, "self": 37.62370119220577 } } } } } } } } } } }, "trainer_advance": { "total": 381.6089602053107, "count": 63298, "self": 1.838492979411967, "children": { "process_trajectory": { "total": 65.42878297987045, "count": 63298, "self": 65.33506517787464, "children": { "RLTrainer._checkpoint": { "total": 0.09371780199580826, "count": 2, "self": 0.09371780199580826 } } }, "_update_policy": { "total": 314.3416842460283, "count": 450, "self": 157.42712767096236, "children": { "TorchPPOOptimizer.update": { "total": 156.91455657506594, "count": 22776, "self": 156.91455657506594 } } } } } } }, "trainer_threads": { "total": 6.720074452459812e-07, "count": 1, "self": 6.720074452459812e-07 }, "TrainerController._save_models": { "total": 0.055510102014523, "count": 1, "self": 0.0008983270090539008, "children": { "RLTrainer._checkpoint": { "total": 0.0546117750054691, "count": 1, "self": 0.0546117750054691 } } } } } } }