{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32625505328178406, "min": 0.32625505328178406, "max": 1.4632600545883179, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9855.5126953125, "min": 9815.5048828125, "max": 44389.45703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.24641400575637817, "min": -0.14500002562999725, "max": 0.2841465473175049, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 62.8355712890625, "min": -34.94500732421875, "max": 72.74151611328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.27104660868644714, "min": -0.27104660868644714, "max": 0.38836491107940674, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -69.11688232421875, "min": -69.11688232421875, "max": 92.04248046875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06710461822097256, "min": 0.06407377053519654, "max": 0.07282707416466326, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9394646550936159, "min": 0.47663762959890504, "max": 1.0195790383052856, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.030380749334220865, "min": 0.0003874038965476482, "max": 0.030380749334220865, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.4253304906790921, "min": 0.004702409028595866, "max": 0.4253304906790921, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.63372602688571e-06, "min": 7.63372602688571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010687216437639996, "min": 0.00010687216437639996, "max": 0.0035072330309224003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254454285714286, "min": 0.10254454285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356236, "min": 1.3691136000000002, "max": 2.5690776, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002641998314285714, "min": 0.0002641998314285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00369879764, "min": 0.00369879764, "max": 0.11693085224, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010915083810687065, "min": 0.010915083810687065, "max": 0.528436541557312, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1528111696243286, "min": 0.1528111696243286, "max": 3.6990559101104736, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 578.0, "min": 568.98, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29478.0, "min": 15984.0, "max": 32333.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.029729378281855, "min": -1.0000000521540642, "max": 1.123003896106692, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 52.51619829237461, "min": -32.000001668930054, "max": 57.27319870144129, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.029729378281855, "min": -1.0000000521540642, "max": 1.123003896106692, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 52.51619829237461, "min": -32.000001668930054, "max": 57.27319870144129, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06601920983224523, "min": 0.06601920983224523, "max": 10.769413832575083, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3669797014445066, "min": 3.3669797014445066, "max": 172.31062132120132, "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": "1711512114", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711514479" }, "total": 2365.5501715929995, "count": 1, "self": 0.48919144999945274, "children": { "run_training.setup": { "total": 0.07516258900000139, "count": 1, "self": 0.07516258900000139 }, "TrainerController.start_learning": { "total": 2364.9858175540003, "count": 1, "self": 1.9399390259532083, "children": { "TrainerController._reset_env": { "total": 2.7314399370000046, "count": 1, "self": 2.7314399370000046 }, "TrainerController.advance": { "total": 2360.2219544790464, "count": 63413, "self": 1.9792104879811632, "children": { "env_step": { "total": 1693.7878072830213, "count": 63413, "self": 1527.9226353090914, "children": { "SubprocessEnvManager._take_step": { "total": 164.7072971670134, "count": 63413, "self": 5.740313942974126, "children": { "TorchPolicy.evaluate": { "total": 158.96698322403927, "count": 62561, "self": 158.96698322403927 } } }, "workers": { "total": 1.1578748069164249, "count": 63413, "self": 0.0, "children": { "worker_root": { "total": 2358.716707561015, "count": 63413, "is_parallel": true, "self": 980.7405752680345, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003184166999972149, "count": 1, "is_parallel": true, "self": 0.0008626329995422566, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023215340004298923, "count": 8, "is_parallel": true, "self": 0.0023215340004298923 } } }, "UnityEnvironment.step": { "total": 0.05512594199990417, "count": 1, "is_parallel": true, "self": 0.0006765329999325331, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004719139999451727, "count": 1, "is_parallel": true, "self": 0.0004719139999451727 }, "communicator.exchange": { "total": 0.052132164000113335, "count": 1, "is_parallel": true, "self": 0.052132164000113335 }, "steps_from_proto": { "total": 0.0018453309999131307, "count": 1, "is_parallel": true, "self": 0.0004080879996308795, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014372430002822512, "count": 8, "is_parallel": true, "self": 0.0014372430002822512 } } } } } } }, "UnityEnvironment.step": { "total": 1377.9761322929805, "count": 63412, "is_parallel": true, "self": 40.03888499999903, "children": { "UnityEnvironment._generate_step_input": { "total": 26.913946678012735, "count": 63412, "is_parallel": true, "self": 26.913946678012735 }, "communicator.exchange": { "total": 1194.470912977984, "count": 63412, "is_parallel": true, "self": 1194.470912977984 }, "steps_from_proto": { "total": 116.5523876369848, "count": 63412, "is_parallel": true, "self": 24.943769079838376, "children": { "_process_rank_one_or_two_observation": { "total": 91.60861855714643, "count": 507296, "is_parallel": true, "self": 91.60861855714643 } } } } } } } } } } }, "trainer_advance": { "total": 664.4549367080442, "count": 63413, "self": 3.4356319379678553, "children": { "process_trajectory": { "total": 136.30736966207587, "count": 63413, "self": 136.04871037207567, "children": { "RLTrainer._checkpoint": { "total": 0.25865929000019605, "count": 2, "self": 0.25865929000019605 } } }, "_update_policy": { "total": 524.7119351080005, "count": 439, "self": 308.45282259501914, "children": { "TorchPPOOptimizer.update": { "total": 216.25911251298135, "count": 22821, "self": 216.25911251298135 } } } } } } }, "trainer_threads": { "total": 1.2159998732386157e-06, "count": 1, "self": 1.2159998732386157e-06 }, "TrainerController._save_models": { "total": 0.09248289600054704, "count": 1, "self": 0.0015630940006303717, "children": { "RLTrainer._checkpoint": { "total": 0.09091980199991667, "count": 1, "self": 0.09091980199991667 } } } } } } }