{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.013842104002833366, "min": 0.009778490290045738, "max": 1.3902080059051514, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 414.59869384765625, "min": 286.6271057128906, "max": 42173.3515625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999976.0, "min": 29952.0, "max": 2999976.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999976.0, "min": 29952.0, "max": 2999976.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0819011703133583, "min": -0.1113419309258461, "max": -0.03630732744932175, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -19.656280517578125, "min": -26.833404541015625, "max": -8.750065803527832, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.9138123989105225, "min": 0.3429158627986908, "max": 0.9473116397857666, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 219.31497192382812, "min": 81.27105712890625, "max": 227.35479736328125, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07110127105098153, "min": 0.06341964541770548, "max": 0.07420766011648981, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9954177947137414, "min": 0.4999419930631873, "max": 1.0182698772102194, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0017044595478327813, "min": 0.000290094300741194, "max": 0.008311883071455637, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.02386243366965894, "min": 0.003771225909635522, "max": 0.05818318150018947, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4818995060666626e-06, "min": 1.4818995060666626e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0746593084933277e-05, "min": 2.0746593084933277e-05, "max": 0.003646552484482533, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049393333333335, "min": 0.10049393333333335, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.406915066666667, "min": 1.3846288, "max": 2.6110059333333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.934393999999986e-05, "min": 5.934393999999986e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000830815159999998, "min": 0.000830815159999998, "max": 0.12156019491999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.9049562215805054, "min": 0.6017931699752808, "max": 0.9343165755271912, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 12.669386863708496, "min": 4.212552070617676, "max": 13.080431938171387, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 970.483870967742, "min": 917.6764705882352, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30085.0, "min": 15984.0, "max": 32604.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8420194058168319, "min": -1.0000000521540642, "max": -0.6242529903264606, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -26.10260158032179, "min": -31.9992016851902, "max": -16.000000834465027, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8420194058168319, "min": -1.0000000521540642, "max": -0.6242529903264606, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -26.10260158032179, "min": -31.9992016851902, "max": -16.000000834465027, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 8.671129838112861, "min": 5.7871694691253435, "max": 10.272705867886543, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 268.8050249814987, "min": 164.3632938861847, "max": 300.01137614250183, "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": "1748853512", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1748858905" }, "total": 5393.451240565, "count": 1, "self": 0.49204613800066, "children": { "run_training.setup": { "total": 0.023159724999914033, "count": 1, "self": 0.023159724999914033 }, "TrainerController.start_learning": { "total": 5392.936034702, "count": 1, "self": 3.6340235059005863, "children": { "TrainerController._reset_env": { "total": 3.5885788369998863, "count": 1, "self": 3.5885788369998863 }, "TrainerController.advance": { "total": 5385.6235014641, "count": 188715, "self": 3.8102806708620847, "children": { "env_step": { "total": 3386.8894527991024, "count": 188715, "self": 2953.989718092854, "children": { "SubprocessEnvManager._take_step": { "total": 430.82000785416267, "count": 188715, "self": 12.987040571126045, "children": { "TorchPolicy.evaluate": { "total": 417.8329672830366, "count": 187547, "self": 417.8329672830366 } } }, "workers": { "total": 2.079726852085514, "count": 188715, "self": 0.0, "children": { "worker_root": { "total": 5380.448258130191, "count": 188715, "is_parallel": true, "self": 2733.315237056103, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00494250099995952, "count": 1, "is_parallel": true, "self": 0.0035985320002964727, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013439689996630477, "count": 8, "is_parallel": true, "self": 0.0013439689996630477 } } }, "UnityEnvironment.step": { "total": 0.04750579200003813, "count": 1, "is_parallel": true, "self": 0.0005386800000906078, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044697499993162637, "count": 1, "is_parallel": true, "self": 0.00044697499993162637 }, "communicator.exchange": { "total": 0.043006933000015124, "count": 1, "is_parallel": true, "self": 0.043006933000015124 }, "steps_from_proto": { "total": 0.003513204000000769, "count": 1, "is_parallel": true, "self": 0.002295204999654743, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012179990003460262, "count": 8, "is_parallel": true, "self": 0.0012179990003460262 } } } } } } }, "UnityEnvironment.step": { "total": 2647.133021074088, "count": 188714, "is_parallel": true, "self": 92.73649816196576, "children": { "UnityEnvironment._generate_step_input": { "total": 67.51823447501965, "count": 188714, "is_parallel": true, "self": 67.51823447501965 }, "communicator.exchange": { "total": 2216.1699291739787, "count": 188714, "is_parallel": true, "self": 2216.1699291739787 }, "steps_from_proto": { "total": 270.7083592631236, "count": 188714, "is_parallel": true, "self": 52.53688368304961, "children": { "_process_rank_one_or_two_observation": { "total": 218.171475580074, "count": 1509712, "is_parallel": true, "self": 218.171475580074 } } } } } } } } } } }, "trainer_advance": { "total": 1994.923767994135, "count": 188715, "self": 6.55811617324639, "children": { "process_trajectory": { "total": 361.25758628388917, "count": 188715, "self": 360.6084377388904, "children": { "RLTrainer._checkpoint": { "total": 0.6491485449987522, "count": 6, "self": 0.6491485449987522 } } }, "_update_policy": { "total": 1627.1080655369994, "count": 1337, "self": 902.0922836769639, "children": { "TorchPPOOptimizer.update": { "total": 725.0157818600355, "count": 68580, "self": 725.0157818600355 } } } } } } }, "trainer_threads": { "total": 9.40000063565094e-07, "count": 1, "self": 9.40000063565094e-07 }, "TrainerController._save_models": { "total": 0.08992995500011602, "count": 1, "self": 0.0015250400001605158, "children": { "RLTrainer._checkpoint": { "total": 0.08840491499995551, "count": 1, "self": 0.08840491499995551 } } } } } } }