{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35597968101501465, "min": 0.3501036763191223, "max": 1.3755429983139038, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10622.43359375, "min": 10622.43359375, "max": 41728.47265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6096248030662537, "min": -0.13656310737133026, "max": 0.7057522535324097, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.3045654296875, "min": -32.365455627441406, "max": 207.4911651611328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01256032008677721, "min": -0.09716853499412537, "max": 0.6835715770721436, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.529449939727783, "min": -24.777976989746094, "max": 162.0064697265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.064877913542746, "min": 0.06464022922141123, "max": 0.07403746912937745, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9082907895984439, "min": 0.4939690001978641, "max": 1.0365245678112842, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013847810829160843, "min": 0.00026925075579887185, "max": 0.022196091161206664, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1938693516082518, "min": 0.0035002598253853342, "max": 0.24550782854203135, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.703668860714287e-06, "min": 7.703668860714287e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010785136405000003, "min": 0.00010785136405000003, "max": 0.0033769267743577994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256785714285714, "min": 0.10256785714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.43595, "min": 1.3886848, "max": 2.4858557000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026652892857142866, "min": 0.00026652892857142866, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003731405000000001, "min": 0.003731405000000001, "max": 0.11258165577999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012877690605819225, "min": 0.012877690605819225, "max": 0.7590191960334778, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1802876740694046, "min": 0.1802876740694046, "max": 5.31313419342041, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 330.6559139784946, "min": 260.7118644067797, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30751.0, "min": 15984.0, "max": 32973.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6478343884791098, "min": -1.0000000521540642, "max": 1.7223372747332364, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.2485981285572, "min": -30.9940015822649, "max": 203.23579841852188, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6478343884791098, "min": -1.0000000521540642, "max": 1.7223372747332364, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.2485981285572, "min": -30.9940015822649, "max": 203.23579841852188, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04409663437681663, "min": 0.03622114349324829, "max": 16.245294569060206, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.100986997043947, "min": 3.81345090616378, "max": 259.9247131049633, "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": "1751183454", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751185753" }, "total": 2299.11943939, "count": 1, "self": 0.48164953700006663, "children": { "run_training.setup": { "total": 0.021274854000012056, "count": 1, "self": 0.021274854000012056 }, "TrainerController.start_learning": { "total": 2298.616514999, "count": 1, "self": 1.5825435289625602, "children": { "TrainerController._reset_env": { "total": 2.151996115999964, "count": 1, "self": 2.151996115999964 }, "TrainerController.advance": { "total": 2294.779937976037, "count": 64107, "self": 1.6152818811001453, "children": { "env_step": { "total": 1634.6778962129376, "count": 64107, "self": 1474.6136622178506, "children": { "SubprocessEnvManager._take_step": { "total": 159.11778540004047, "count": 64107, "self": 4.851932482092479, "children": { "TorchPolicy.evaluate": { "total": 154.265852917948, "count": 62578, "self": 154.265852917948 } } }, "workers": { "total": 0.9464485950466042, "count": 64107, "self": 0.0, "children": { "worker_root": { "total": 2292.8609194439227, "count": 64107, "is_parallel": true, "self": 938.2379959349717, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017246139998405852, "count": 1, "is_parallel": true, "self": 0.000574544000073729, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011500699997668562, "count": 8, "is_parallel": true, "self": 0.0011500699997668562 } } }, "UnityEnvironment.step": { "total": 0.052735074000111126, "count": 1, "is_parallel": true, "self": 0.0005864690001544659, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004627329999493668, "count": 1, "is_parallel": true, "self": 0.0004627329999493668 }, "communicator.exchange": { "total": 0.0499548440000126, "count": 1, "is_parallel": true, "self": 0.0499548440000126 }, "steps_from_proto": { "total": 0.0017310279999946943, "count": 1, "is_parallel": true, "self": 0.00039942699959283345, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013316010004018608, "count": 8, "is_parallel": true, "self": 0.0013316010004018608 } } } } } } }, "UnityEnvironment.step": { "total": 1354.622923508951, "count": 64106, "is_parallel": true, "self": 32.49463317693812, "children": { "UnityEnvironment._generate_step_input": { "total": 22.887184078949076, "count": 64106, "is_parallel": true, "self": 22.887184078949076 }, "communicator.exchange": { "total": 1200.9146397920404, "count": 64106, "is_parallel": true, "self": 1200.9146397920404 }, "steps_from_proto": { "total": 98.32646646102353, "count": 64106, "is_parallel": true, "self": 20.575091587266115, "children": { "_process_rank_one_or_two_observation": { "total": 77.75137487375741, "count": 512848, "is_parallel": true, "self": 77.75137487375741 } } } } } } } } } } }, "trainer_advance": { "total": 658.4867598819994, "count": 64107, "self": 3.04866648503139, "children": { "process_trajectory": { "total": 127.3451995439691, "count": 64107, "self": 127.12471074096993, "children": { "RLTrainer._checkpoint": { "total": 0.22048880299917073, "count": 2, "self": 0.22048880299917073 } } }, "_update_policy": { "total": 528.0928938529989, "count": 451, "self": 294.9963582789826, "children": { "TorchPPOOptimizer.update": { "total": 233.09653557401634, "count": 22809, "self": 233.09653557401634 } } } } } } }, "trainer_threads": { "total": 1.8949995137518272e-06, "count": 1, "self": 1.8949995137518272e-06 }, "TrainerController._save_models": { "total": 0.10203548300069087, "count": 1, "self": 0.001099986000554054, "children": { "RLTrainer._checkpoint": { "total": 0.10093549700013682, "count": 1, "self": 0.10093549700013682 } } } } } } }