{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5136916637420654, "min": 0.47984686493873596, "max": 1.4610569477081299, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15509.3779296875, "min": 14387.728515625, "max": 44322.625, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29957.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29957.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.39661839604377747, "min": -0.25488948822021484, "max": 0.4314587712287903, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 104.31063842773438, "min": -60.6636962890625, "max": 115.63095092773438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.06360981613397598, "min": -0.05024896189570427, "max": 0.25392967462539673, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.729381561279297, "min": -13.114978790283203, "max": 61.197052001953125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06761027507068842, "min": 0.06452883116082174, "max": 0.07534480527032254, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9465438509896379, "min": 0.5274136368922578, "max": 1.067362092097527, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013331314005242274, "min": 0.0008643357842834019, "max": 0.013331314005242274, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18663839607339183, "min": 0.011236365195684226, "max": 0.18663839607339183, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.676926012485715e-06, "min": 7.676926012485715e-06, "max": 0.00029523818730155715, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010747696417480002, "min": 0.00010747696417480002, "max": 0.0035078597307134996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255894285714286, "min": 0.10255894285714286, "max": 0.19841272857142855, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358252, "min": 1.3888890999999999, "max": 2.5692865000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002656383914285716, "min": 0.0002656383914285716, "max": 0.009841431584285715, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003718937480000002, "min": 0.003718937480000002, "max": 0.11695172135, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005772557575255632, "min": 0.005641849245876074, "max": 0.3821871280670166, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08081580698490143, "min": 0.07898589223623276, "max": 2.675309896469116, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 488.0153846153846, "min": 447.2258064516129, "max": 982.1515151515151, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31721.0, "min": 16500.0, "max": 32827.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2749817909842187, "min": -0.9225152031038747, "max": 1.4897969465589884, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 84.14879820495844, "min": -30.443001702427864, "max": 98.32659847289324, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2749817909842187, "min": -0.9225152031038747, "max": 1.4897969465589884, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 84.14879820495844, "min": -30.443001702427864, "max": 98.32659847289324, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028460808315492504, "min": 0.027632859321649866, "max": 7.43223214982187, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8784133488225052, "min": 1.6856044186206418, "max": 126.3479465469718, "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": "1772813671", "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": "1772815840" }, "total": 2169.1624674059995, "count": 1, "self": 0.4323288049999974, "children": { "run_training.setup": { "total": 0.03480717599995842, "count": 1, "self": 0.03480717599995842 }, "TrainerController.start_learning": { "total": 2168.6953314249995, "count": 1, "self": 1.367644053132608, "children": { "TrainerController._reset_env": { "total": 2.3987721330004206, "count": 1, "self": 2.3987721330004206 }, "TrainerController.advance": { "total": 2164.852680644867, "count": 63562, "self": 1.5240075399906345, "children": { "env_step": { "total": 1494.1681730648752, "count": 63562, "self": 1338.091603087776, "children": { "SubprocessEnvManager._take_step": { "total": 155.235520973004, "count": 63562, "self": 4.7977922642967314, "children": { "TorchPolicy.evaluate": { "total": 150.43772870870725, "count": 62566, "self": 150.43772870870725 } } }, "workers": { "total": 0.8410490040951117, "count": 63562, "self": 0.0, "children": { "worker_root": { "total": 2161.8745650100564, "count": 63562, "is_parallel": true, "self": 943.8429021539405, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018886439993366366, "count": 1, "is_parallel": true, "self": 0.0006622290020459332, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012264149972907035, "count": 8, "is_parallel": true, "self": 0.0012264149972907035 } } }, "UnityEnvironment.step": { "total": 0.05605680100052268, "count": 1, "is_parallel": true, "self": 0.0006195850000949576, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000542961000064679, "count": 1, "is_parallel": true, "self": 0.000542961000064679 }, "communicator.exchange": { "total": 0.05311602900019352, "count": 1, "is_parallel": true, "self": 0.05311602900019352 }, "steps_from_proto": { "total": 0.001778226000169525, "count": 1, "is_parallel": true, "self": 0.0003571109991753474, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014211150009941775, "count": 8, "is_parallel": true, "self": 0.0014211150009941775 } } } } } } }, "UnityEnvironment.step": { "total": 1218.0316628561159, "count": 63561, "is_parallel": true, "self": 34.61992517315139, "children": { "UnityEnvironment._generate_step_input": { "total": 24.11810555196007, "count": 63561, "is_parallel": true, "self": 24.11810555196007 }, "communicator.exchange": { "total": 1047.2786508450254, "count": 63561, "is_parallel": true, "self": 1047.2786508450254 }, "steps_from_proto": { "total": 112.01498128597905, "count": 63561, "is_parallel": true, "self": 23.571188087653354, "children": { "_process_rank_one_or_two_observation": { "total": 88.4437931983257, "count": 508488, "is_parallel": true, "self": 88.4437931983257 } } } } } } } } } } }, "trainer_advance": { "total": 669.1605000400014, "count": 63562, "self": 2.6153286940125327, "children": { "process_trajectory": { "total": 124.6677258389891, "count": 63562, "self": 124.47078770399003, "children": { "RLTrainer._checkpoint": { "total": 0.19693813499907264, "count": 2, "self": 0.19693813499907264 } } }, "_update_policy": { "total": 541.8774455069997, "count": 452, "self": 301.2027007800134, "children": { "TorchPPOOptimizer.update": { "total": 240.67474472698632, "count": 22791, "self": 240.67474472698632 } } } } } } }, "trainer_threads": { "total": 8.899996828404255e-07, "count": 1, "self": 8.899996828404255e-07 }, "TrainerController._save_models": { "total": 0.0762337039996055, "count": 1, "self": 0.000980993999291968, "children": { "RLTrainer._checkpoint": { "total": 0.07525271000031353, "count": 1, "self": 0.07525271000031353 } } } } } } }