{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14280743896961212, "min": 0.13818636536598206, "max": 1.4633220434188843, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4293.36279296875, "min": 4103.58251953125, "max": 44391.3359375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999901.0, "min": 29952.0, "max": 2999901.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999901.0, "min": 29952.0, "max": 2999901.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8156636953353882, "min": -0.10103955864906311, "max": 0.9036851525306702, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 245.5147705078125, "min": -24.45157241821289, "max": 280.14239501953125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014001032337546349, "min": -0.04318656399846077, "max": 0.36548855900764465, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.214310646057129, "min": -10.926200866699219, "max": 86.62078857421875, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06845179736791622, "min": 0.06272790234905071, "max": 0.07504414065070229, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.958325163150827, "min": 0.49780014440438697, "max": 1.0608395482915656, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014363895175241243, "min": 0.00034970744883078, "max": 0.01763231658073242, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2010945324533774, "min": 0.00419648938596936, "max": 0.24685243213025387, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.485228076385716e-06, "min": 1.485228076385716e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0793193069400022e-05, "min": 2.0793193069400022e-05, "max": 0.003968951577016166, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049504285714285, "min": 0.10049504285714285, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069306, "min": 1.3962282666666668, "max": 2.7525246000000005, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9454781428571485e-05, "min": 5.9454781428571485e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008323669400000008, "min": 0.0008323669400000008, "max": 0.13230608494999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005520425736904144, "min": 0.005485298577696085, "max": 0.5199190378189087, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07728596031665802, "min": 0.07728596031665802, "max": 3.6394331455230713, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 228.34375, "min": 206.06474820143885, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29228.0, "min": 15984.0, "max": 33209.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7403952978202142, "min": -1.0000000521540642, "max": 1.7939352364205627, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 222.77059812098742, "min": -31.998401656746864, "max": 253.590997710824, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7403952978202142, "min": -1.0000000521540642, "max": 1.7939352364205627, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 222.77059812098742, "min": -31.998401656746864, "max": 253.590997710824, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013073411428308646, "min": 0.012292344707661164, "max": 10.69173732586205, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6733966628235066, "min": 1.6554624012933346, "max": 171.0677972137928, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1785290201", "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": "1785300165" }, "total": 9964.010561595001, "count": 1, "self": 0.4790026030023, "children": { "run_training.setup": { "total": 0.02824461499994868, "count": 1, "self": 0.02824461499994868 }, "TrainerController.start_learning": { "total": 9963.503314377, "count": 1, "self": 5.967677134785845, "children": { "TrainerController._reset_env": { "total": 2.4221490079999057, "count": 1, "self": 2.4221490079999057 }, "TrainerController.advance": { "total": 9955.032944610215, "count": 194776, "self": 6.214308647095095, "children": { "env_step": { "total": 7667.329358111002, "count": 194776, "self": 7053.170723272273, "children": { "SubprocessEnvManager._take_step": { "total": 610.4611874448665, "count": 194776, "self": 18.01653528391398, "children": { "TorchPolicy.evaluate": { "total": 592.4446521609525, "count": 187564, "self": 592.4446521609525 } } }, "workers": { "total": 3.697447393863058, "count": 194776, "self": 0.0, "children": { "worker_root": { "total": 9942.324176570171, "count": 194776, "is_parallel": true, "self": 3368.048026751987, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002086856000005355, "count": 1, "is_parallel": true, "self": 0.0006864360000236047, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014004199999817502, "count": 8, "is_parallel": true, "self": 0.0014004199999817502 } } }, "UnityEnvironment.step": { "total": 0.06185051000011299, "count": 1, "is_parallel": true, "self": 0.0006236980002540804, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005590010000560142, "count": 1, "is_parallel": true, "self": 0.0005590010000560142 }, "communicator.exchange": { "total": 0.058660017999955016, "count": 1, "is_parallel": true, "self": 0.058660017999955016 }, "steps_from_proto": { "total": 0.0020077929998478794, "count": 1, "is_parallel": true, "self": 0.0004621249991032528, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015456680007446266, "count": 8, "is_parallel": true, "self": 0.0015456680007446266 } } } } } } }, "UnityEnvironment.step": { "total": 6574.276149818184, "count": 194775, "is_parallel": true, "self": 126.22423868476926, "children": { "UnityEnvironment._generate_step_input": { "total": 87.66725014712665, "count": 194775, "is_parallel": true, "self": 87.66725014712665 }, "communicator.exchange": { "total": 5939.873369345933, "count": 194775, "is_parallel": true, "self": 5939.873369345933 }, "steps_from_proto": { "total": 420.5112916403559, "count": 194775, "is_parallel": true, "self": 84.27840419445602, "children": { "_process_rank_one_or_two_observation": { "total": 336.2328874458999, "count": 1558200, "is_parallel": true, "self": 336.2328874458999 } } } } } } } } } } }, "trainer_advance": { "total": 2281.489277852118, "count": 194776, "self": 11.9832699893077, "children": { "process_trajectory": { "total": 417.47297203381004, "count": 194776, "self": 416.8497563738106, "children": { "RLTrainer._checkpoint": { "total": 0.6232156599994596, "count": 6, "self": 0.6232156599994596 } } }, "_update_policy": { "total": 1852.0330358290003, "count": 1394, "self": 989.4156551500228, "children": { "TorchPPOOptimizer.update": { "total": 862.6173806789775, "count": 68373, "self": 862.6173806789775 } } } } } } }, "trainer_threads": { "total": 1.22199890029151e-06, "count": 1, "self": 1.22199890029151e-06 }, "TrainerController._save_models": { "total": 0.08054240199999185, "count": 1, "self": 0.0010554749987932155, "children": { "RLTrainer._checkpoint": { "total": 0.07948692700119864, "count": 1, "self": 0.07948692700119864 } } } } } } }