{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.06137547269463539, "min": 0.050522513687610626, "max": 1.4060906171798706, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 1838.318115234375, "min": 1493.9769287109375, "max": 42655.1640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08396873623132706, "min": -0.26935309171676636, "max": -0.03601357713341713, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -20.236465454101562, "min": -63.8366813659668, "max": -8.679271697998047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.4639581441879272, "min": 0.3903111219406128, "max": 1.49992835521698, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 352.81390380859375, "min": 92.50373840332031, "max": 361.48272705078125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07107425820902877, "min": 0.06510305120041714, "max": 0.0724374112231863, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9950396149264027, "min": 0.5070618785623041, "max": 1.0094984276334333, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007296895039048866, "min": 0.005370183632630408, "max": 0.009928878643871996, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10215653054668412, "min": 0.05564978032781182, "max": 0.12907542237033595, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.755268843514292e-06, "min": 7.755268843514292e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001085737638092001, "min": 0.0001085737638092001, "max": 0.003507260630913199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258505714285715, "min": 0.10258505714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361908, "min": 1.3886848, "max": 2.5690868000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002682472085714288, "min": 0.0002682472085714288, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037554609200000032, "min": 0.0037554609200000032, "max": 0.11693177131999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 1.481525182723999, "min": 0.5790585279464722, "max": 1.5078221559524536, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 20.741352081298828, "min": 4.053409576416016, "max": 21.10951042175293, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 960.7, "min": 954.4375, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28821.0, "min": 15984.0, "max": 32687.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8278400468329589, "min": -1.0000000521540642, "max": -0.689110394438793, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -24.835201404988766, "min": -31.992801636457443, "max": -16.000000834465027, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8278400468329589, "min": -1.0000000521540642, "max": -0.689110394438793, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -24.835201404988766, "min": -31.992801636457443, "max": -16.000000834465027, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 13.982780611515045, "min": 8.151590535812305, "max": 14.856133223542322, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 419.48341834545135, "min": 131.05368986725807, "max": 469.9335271801101, "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": "1753888422", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training1.2 --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": "1753890110" }, "total": 1687.435682141, "count": 1, "self": 0.32523584899990965, "children": { "run_training.setup": { "total": 0.030050496000058047, "count": 1, "self": 0.030050496000058047 }, "TrainerController.start_learning": { "total": 1687.080395796, "count": 1, "self": 1.4621887789587618, "children": { "TrainerController._reset_env": { "total": 2.323750393999944, "count": 1, "self": 2.323750393999944 }, "TrainerController.advance": { "total": 1683.2044586260413, "count": 63153, "self": 1.4010175761266055, "children": { "env_step": { "total": 1050.020917751944, "count": 63153, "self": 895.337604806866, "children": { "SubprocessEnvManager._take_step": { "total": 153.79925989404046, "count": 63153, "self": 4.632093157054442, "children": { "TorchPolicy.evaluate": { "total": 149.16716673698602, "count": 62570, "self": 149.16716673698602 } } }, "workers": { "total": 0.8840530510374265, "count": 63153, "self": 0.0, "children": { "worker_root": { "total": 1684.6595662649954, "count": 63153, "is_parallel": true, "self": 885.3223912709818, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002013746999864452, "count": 1, "is_parallel": true, "self": 0.0006444959999498678, "children": { "_process_rank_one_or_two_observation": { "total": 0.001369250999914584, "count": 8, "is_parallel": true, "self": 0.001369250999914584 } } }, "UnityEnvironment.step": { "total": 0.04483826199998475, "count": 1, "is_parallel": true, "self": 0.000355892000015956, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003101449999576289, "count": 1, "is_parallel": true, "self": 0.0003101449999576289 }, "communicator.exchange": { "total": 0.04310467499999504, "count": 1, "is_parallel": true, "self": 0.04310467499999504 }, "steps_from_proto": { "total": 0.0010675500000161264, "count": 1, "is_parallel": true, "self": 0.0002616599995235447, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008058900004925817, "count": 8, "is_parallel": true, "self": 0.0008058900004925817 } } } } } } }, "UnityEnvironment.step": { "total": 799.3371749940136, "count": 63152, "is_parallel": true, "self": 20.261309982113062, "children": { "UnityEnvironment._generate_step_input": { "total": 14.050121337920928, "count": 63152, "is_parallel": true, "self": 14.050121337920928 }, "communicator.exchange": { "total": 704.265375135963, "count": 63152, "is_parallel": true, "self": 704.265375135963 }, "steps_from_proto": { "total": 60.760368538016564, "count": 63152, "is_parallel": true, "self": 13.176876046171401, "children": { "_process_rank_one_or_two_observation": { "total": 47.58349249184516, "count": 505216, "is_parallel": true, "self": 47.58349249184516 } } } } } } } } } } }, "trainer_advance": { "total": 631.7825232979708, "count": 63153, "self": 2.6800112389055357, "children": { "process_trajectory": { "total": 116.37301919906213, "count": 63153, "self": 116.16728786006252, "children": { "RLTrainer._checkpoint": { "total": 0.2057313389996125, "count": 2, "self": 0.2057313389996125 } } }, "_update_policy": { "total": 512.7294928600031, "count": 443, "self": 283.04561531001127, "children": { "TorchPPOOptimizer.update": { "total": 229.68387754999185, "count": 22767, "self": 229.68387754999185 } } } } } } }, "trainer_threads": { "total": 9.830000635702163e-07, "count": 1, "self": 9.830000635702163e-07 }, "TrainerController._save_models": { "total": 0.08999701399989135, "count": 1, "self": 0.0011957709998569044, "children": { "RLTrainer._checkpoint": { "total": 0.08880124300003445, "count": 1, "self": 0.08880124300003445 } } } } } } }