{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3877318203449249, "min": 0.36068210005760193, "max": 1.5218136310577393, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 11656.76953125, "min": 10716.5869140625, "max": 46165.73828125, "count": 40 }, "Pyramids.Step.mean": { "value": 1199953.0, "min": 29952.0, "max": 1199953.0, "count": 40 }, "Pyramids.Step.sum": { "value": 1199953.0, "min": 29952.0, "max": 1199953.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5595714449882507, "min": -0.11484373360872269, "max": 0.6875190734863281, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 155.0012969970703, "min": -27.562496185302734, "max": 191.1302947998047, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.013597299344837666, "min": -0.013597299344837666, "max": 0.17450758814811707, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.766451835632324, "min": -3.766451835632324, "max": 41.358299255371094, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07030064104977149, "min": 0.06446827472672063, "max": 0.07717752647350086, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9842089746968009, "min": 0.540242685314506, "max": 1.0916999377853547, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015933876425006325, "min": 0.0001379703049237267, "max": 0.016838000299772136, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22307426995008856, "min": 0.0017936139640084472, "max": 0.2357320041968099, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00018148777521837385, "min": 0.00018148777521837385, "max": 0.00029838354339596195, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002540828853057234, "min": 0.0020886848037717336, "max": 0.0038025892324703332, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16049591190476192, "min": 0.16049591190476192, "max": 0.19946118095238097, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.246942766666667, "min": 1.3962282666666668, "max": 2.7675296666666673, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 0.006053541599285714, "min": 0.006053541599285714, "max": 0.009946171977142856, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.08474958239, "min": 0.06962320384, "max": 0.1267762137, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006570899393409491, "min": 0.006375475786626339, "max": 0.32541850209236145, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09199259430170059, "min": 0.09186342358589172, "max": 2.2779295444488525, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 354.09638554216866, "min": 300.8137254901961, "max": 999.0, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29390.0, "min": 16879.0, "max": 32291.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5976987728871495, "min": -0.9999750521965325, "max": 1.650879978686571, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.6089981496334, "min": -31.99920167028904, "max": 165.31379801034927, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5976987728871495, "min": -0.9999750521965325, "max": 1.650879978686571, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.6089981496334, "min": -31.99920167028904, "max": 165.31379801034927, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02439988254610146, "min": 0.020327988417554534, "max": 6.845169574898832, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0251902513264213, "min": 1.8916955800086726, "max": 116.36788277328014, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1788941063", "python_version": "3.10.12 (main, Aug 31 2026, 10:18:17) [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=PyramidsTraining --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": "1788943926" }, "total": 2863.330854128, "count": 1, "self": 0.4445133590002115, "children": { "run_training.setup": { "total": 0.020604360999641358, "count": 1, "self": 0.020604360999641358 }, "TrainerController.start_learning": { "total": 2862.865736408, "count": 1, "self": 1.7079324958872348, "children": { "TrainerController._reset_env": { "total": 2.738941387000068, "count": 1, "self": 2.738941387000068 }, "TrainerController.advance": { "total": 2858.2828334761125, "count": 78396, "self": 1.811316683055793, "children": { "env_step": { "total": 2064.8288732480396, "count": 78396, "self": 1873.1829407109371, "children": { "SubprocessEnvManager._take_step": { "total": 190.60180326904083, "count": 78396, "self": 5.897691541081258, "children": { "TorchPolicy.evaluate": { "total": 184.70411172795957, "count": 76771, "self": 184.70411172795957 } } }, "workers": { "total": 1.0441292680616243, "count": 78395, "self": 0.0, "children": { "worker_root": { "total": 2855.88467323092, "count": 78395, "is_parallel": true, "self": 1129.8653481779334, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019311969999762368, "count": 1, "is_parallel": true, "self": 0.0005923559997427219, "children": { "_process_rank_one_or_two_observation": { "total": 0.001338841000233515, "count": 8, "is_parallel": true, "self": 0.001338841000233515 } } }, "UnityEnvironment.step": { "total": 0.05080800099995031, "count": 1, "is_parallel": true, "self": 0.0005484409998643969, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004664130001401645, "count": 1, "is_parallel": true, "self": 0.0004664130001401645 }, "communicator.exchange": { "total": 0.047895737000089866, "count": 1, "is_parallel": true, "self": 0.047895737000089866 }, "steps_from_proto": { "total": 0.0018974099998558813, "count": 1, "is_parallel": true, "self": 0.00042792699969140813, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014694830001644732, "count": 8, "is_parallel": true, "self": 0.0014694830001644732 } } } } } } }, "UnityEnvironment.step": { "total": 1726.0193250529865, "count": 78394, "is_parallel": true, "self": 42.48915618807132, "children": { "UnityEnvironment._generate_step_input": { "total": 30.350658582993674, "count": 78394, "is_parallel": true, "self": 30.350658582993674 }, "communicator.exchange": { "total": 1513.377495855057, "count": 78394, "is_parallel": true, "self": 1513.377495855057 }, "steps_from_proto": { "total": 139.8020144268644, "count": 78394, "is_parallel": true, "self": 29.356458474928786, "children": { "_process_rank_one_or_two_observation": { "total": 110.4455559519356, "count": 627152, "is_parallel": true, "self": 110.4455559519356 } } } } } } } } } } }, "trainer_advance": { "total": 791.6426435450171, "count": 78395, "self": 3.168932727981428, "children": { "process_trajectory": { "total": 140.08153779104168, "count": 78395, "self": 139.89009955304164, "children": { "RLTrainer._checkpoint": { "total": 0.1914382380000461, "count": 2, "self": 0.1914382380000461 } } }, "_update_policy": { "total": 648.392173025994, "count": 548, "self": 344.60192527898516, "children": { "TorchPPOOptimizer.update": { "total": 303.79024774700883, "count": 28041, "self": 303.79024774700883 } } } } } } }, "trainer_threads": { "total": 1.4139995982986875e-06, "count": 1, "self": 1.4139995982986875e-06 }, "TrainerController._save_models": { "total": 0.13602763500057335, "count": 1, "self": 0.0014596609998989152, "children": { "RLTrainer._checkpoint": { "total": 0.13456797400067444, "count": 1, "self": 0.13456797400067444 } } } } } } }