{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.33601921796798706, "min": 0.33601921796798706, "max": 1.4777657985687256, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10064.447265625, "min": 10064.447265625, "max": 44829.50390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5399340391159058, "min": -0.0967630073428154, "max": 0.547417402267456, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.94192504882812, "min": -23.31988525390625, "max": 149.4449462890625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006647979840636253, "min": 0.0004736781702376902, "max": 0.28383827209472656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.8215464353561401, "min": 0.1293141394853592, "max": 68.12118530273438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06988137143235902, "min": 0.06453820744786817, "max": 0.0750581545575865, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9783392000530262, "min": 0.4847108351816718, "max": 1.0758356108805553, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015484873201856708, "min": 0.00017512935984253822, "max": 0.016349980463842038, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2167882248259939, "min": 0.0024518110377955353, "max": 0.22889972649378854, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.692483150157142e-06, "min": 7.692483150157142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010769476410219999, "min": 0.00010769476410219999, "max": 0.0035078348307217995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256412857142859, "min": 0.10256412857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358978000000002, "min": 1.3691136000000002, "max": 2.5692782000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002661564442857142, "min": 0.0002661564442857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003726190219999999, "min": 0.003726190219999999, "max": 0.11695089218, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01065827440470457, "min": 0.01065827440470457, "max": 0.3802643418312073, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14921584725379944, "min": 0.14921584725379944, "max": 2.6618504524230957, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 368.3164556962025, "min": 348.16483516483515, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29097.0, "min": 15984.0, "max": 31968.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5847424841485918, "min": -1.0000000521540642, "max": 1.5847424841485918, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.77939873188734, "min": -32.000001668930054, "max": 138.43559774756432, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5847424841485918, "min": -1.0000000521540642, "max": 1.5847424841485918, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.77939873188734, "min": -32.000001668930054, "max": 138.43559774756432, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040260502757882934, "min": 0.040260502757882934, "max": 7.328478837385774, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2208402206306346, "min": 3.2208402206306346, "max": 117.25566139817238, "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": "1754491136", "python_version": "3.10.12 (main, May 27 2025, 17:12:29) [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 --resume", "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": "1754494459" }, "total": 3323.239466188, "count": 1, "self": 0.630568775998654, "children": { "run_training.setup": { "total": 0.04126150600041001, "count": 1, "self": 0.04126150600041001 }, "TrainerController.start_learning": { "total": 3322.5676359060008, "count": 1, "self": 2.4733461811456436, "children": { "TrainerController._reset_env": { "total": 2.8643716060005318, "count": 1, "self": 2.8643716060005318 }, "TrainerController.advance": { "total": 3317.1408338368537, "count": 63706, "self": 2.595620373094789, "children": { "env_step": { "total": 2172.2769509558784, "count": 63706, "self": 2000.129227501655, "children": { "SubprocessEnvManager._take_step": { "total": 170.6686498371064, "count": 63706, "self": 7.861895562137761, "children": { "TorchPolicy.evaluate": { "total": 162.80675427496863, "count": 62569, "self": 162.80675427496863 } } }, "workers": { "total": 1.4790736171171375, "count": 63706, "self": 0.0, "children": { "worker_root": { "total": 3313.271798868992, "count": 63706, "is_parallel": true, "self": 1501.2102145958752, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022949000003791298, "count": 1, "is_parallel": true, "self": 0.0008713959987289854, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014235040016501443, "count": 8, "is_parallel": true, "self": 0.0014235040016501443 } } }, "UnityEnvironment.step": { "total": 0.0752885679994506, "count": 1, "is_parallel": true, "self": 0.0006554669989782269, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005384679998314823, "count": 1, "is_parallel": true, "self": 0.0005384679998314823 }, "communicator.exchange": { "total": 0.0704681420002089, "count": 1, "is_parallel": true, "self": 0.0704681420002089 }, "steps_from_proto": { "total": 0.0036264910004319972, "count": 1, "is_parallel": true, "self": 0.00043796100271720206, "children": { "_process_rank_one_or_two_observation": { "total": 0.003188529997714795, "count": 8, "is_parallel": true, "self": 0.003188529997714795 } } } } } } }, "UnityEnvironment.step": { "total": 1812.0615842731168, "count": 63705, "is_parallel": true, "self": 47.21979905541957, "children": { "UnityEnvironment._generate_step_input": { "total": 31.673504327863157, "count": 63705, "is_parallel": true, "self": 31.673504327863157 }, "communicator.exchange": { "total": 1599.3031401090075, "count": 63705, "is_parallel": true, "self": 1599.3031401090075 }, "steps_from_proto": { "total": 133.86514078082655, "count": 63705, "is_parallel": true, "self": 29.3346458529777, "children": { "_process_rank_one_or_two_observation": { "total": 104.53049492784885, "count": 509640, "is_parallel": true, "self": 104.53049492784885 } } } } } } } } } } }, "trainer_advance": { "total": 1142.2682625078805, "count": 63706, "self": 4.634061694998309, "children": { "process_trajectory": { "total": 172.56650646887738, "count": 63706, "self": 172.29561510987787, "children": { "RLTrainer._checkpoint": { "total": 0.27089135899950634, "count": 2, "self": 0.27089135899950634 } } }, "_update_policy": { "total": 965.0676943440048, "count": 443, "self": 378.35764279694376, "children": { "TorchPPOOptimizer.update": { "total": 586.7100515470611, "count": 22806, "self": 586.7100515470611 } } } } } } }, "trainer_threads": { "total": 1.4590004866477102e-06, "count": 1, "self": 1.4590004866477102e-06 }, "TrainerController._save_models": { "total": 0.08908282300035353, "count": 1, "self": 0.0026034769998659613, "children": { "RLTrainer._checkpoint": { "total": 0.08647934600048757, "count": 1, "self": 0.08647934600048757 } } } } } } }