{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16452611982822418, "min": 0.15992768108844757, "max": 1.4067063331604004, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4977.90234375, "min": 4787.59521484375, "max": 42673.84375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999938.0, "min": 29952.0, "max": 2999938.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999938.0, "min": 29952.0, "max": 2999938.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.768559992313385, "min": -0.16884998977184296, "max": 0.8807933926582336, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 225.18807983398438, "min": -40.01744842529297, "max": 276.5691223144531, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0028777390252798796, "min": -0.010650582611560822, "max": 0.4846550524234772, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8431775569915771, "min": -3.1312713623046875, "max": 114.86325073242188, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07145320943737815, "min": 0.06540813635163568, "max": 0.0740180972918299, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0717981415606723, "min": 0.5127938587959333, "max": 1.1102714593774485, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016106926430560026, "min": 0.00047085786685550186, "max": 0.017927512619438906, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24160389645840039, "min": 0.004708578668555018, "max": 0.24160389645840039, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5054528315488879e-06, "min": 1.5054528315488879e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.258179247323332e-05, "min": 2.258179247323332e-05, "max": 0.003926788491070534, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050178444444444, "min": 0.10050178444444444, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075267666666665, "min": 1.3962282666666668, "max": 2.7675932666666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0128265999999965e-05, "min": 6.0128265999999965e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009019239899999995, "min": 0.0009019239899999995, "max": 0.13090205372, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004428351763635874, "min": 0.004349065013229847, "max": 0.5541973114013672, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06642527878284454, "min": 0.060985103249549866, "max": 3.8793811798095703, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 255.47058823529412, "min": 210.74305555555554, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30401.0, "min": 15984.0, "max": 33265.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7109092303684779, "min": -1.0000000521540642, "max": 1.7885594282533739, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 203.59819841384888, "min": -31.999601677060127, "max": 258.2543973624706, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7109092303684779, "min": -1.0000000521540642, "max": 1.7885594282533739, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 203.59819841384888, "min": -31.999601677060127, "max": 258.2543973624706, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011781243064456439, "min": 0.00979945557293234, "max": 11.693373629823327, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4019679246703163, "min": 1.3131270467729337, "max": 187.09397807717323, "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": "1734083235", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=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+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734094226" }, "total": 10990.803072541, "count": 1, "self": 0.612567307001882, "children": { "run_training.setup": { "total": 0.08264211599998816, "count": 1, "self": 0.08264211599998816 }, "TrainerController.start_learning": { "total": 10990.107863117999, "count": 1, "self": 7.62361902036173, "children": { "TrainerController._reset_env": { "total": 3.189848936999624, "count": 1, "self": 3.189848936999624 }, "TrainerController.advance": { "total": 10979.203173460639, "count": 194876, "self": 7.912797850285642, "children": { "env_step": { "total": 7628.27419350255, "count": 194876, "self": 7130.316035624321, "children": { "SubprocessEnvManager._take_step": { "total": 493.39593531977243, "count": 194876, "self": 22.67708508656051, "children": { "TorchPolicy.evaluate": { "total": 470.7188502332119, "count": 187570, "self": 470.7188502332119 } } }, "workers": { "total": 4.562222558456597, "count": 194876, "self": 0.0, "children": { "worker_root": { "total": 10966.452570094403, "count": 194876, "is_parallel": true, "self": 4405.131007238224, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035061469998254324, "count": 1, "is_parallel": true, "self": 0.0012245570005688933, "children": { "_process_rank_one_or_two_observation": { "total": 0.002281589999256539, "count": 8, "is_parallel": true, "self": 0.002281589999256539 } } }, "UnityEnvironment.step": { "total": 0.0901501799999096, "count": 1, "is_parallel": true, "self": 0.0008431109999946784, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005476010001075338, "count": 1, "is_parallel": true, "self": 0.0005476010001075338 }, "communicator.exchange": { "total": 0.08647125999959826, "count": 1, "is_parallel": true, "self": 0.08647125999959826 }, "steps_from_proto": { "total": 0.0022882080002091243, "count": 1, "is_parallel": true, "self": 0.0005611260003206553, "children": { "_process_rank_one_or_two_observation": { "total": 0.001727081999888469, "count": 8, "is_parallel": true, "self": 0.001727081999888469 } } } } } } }, "UnityEnvironment.step": { "total": 6561.321562856179, "count": 194875, "is_parallel": true, "self": 157.4775327282896, "children": { "UnityEnvironment._generate_step_input": { "total": 99.3603123642979, "count": 194875, "is_parallel": true, "self": 99.3603123642979 }, "communicator.exchange": { "total": 5897.390814415477, "count": 194875, "is_parallel": true, "self": 5897.390814415477 }, "steps_from_proto": { "total": 407.0929033481152, "count": 194875, "is_parallel": true, "self": 88.7022366592355, "children": { "_process_rank_one_or_two_observation": { "total": 318.3906666888797, "count": 1559000, "is_parallel": true, "self": 318.3906666888797 } } } } } } } } } } }, "trainer_advance": { "total": 3343.0161821078036, "count": 194876, "self": 14.991015072019763, "children": { "process_trajectory": { "total": 529.8058547137753, "count": 194876, "self": 529.0980079637766, "children": { "RLTrainer._checkpoint": { "total": 0.70784674999868, "count": 6, "self": 0.70784674999868 } } }, "_update_policy": { "total": 2798.2193123220086, "count": 1396, "self": 1147.849712469173, "children": { "TorchPPOOptimizer.update": { "total": 1650.3695998528356, "count": 68379, "self": 1650.3695998528356 } } } } } } }, "trainer_threads": { "total": 1.1949996405746788e-06, "count": 1, "self": 1.1949996405746788e-06 }, "TrainerController._save_models": { "total": 0.0912205049990007, "count": 1, "self": 0.0025864559993351577, "children": { "RLTrainer._checkpoint": { "total": 0.08863404899966554, "count": 1, "self": 0.08863404899966554 } } } } } } }