{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4350137710571289, "min": 0.4265413284301758, "max": 1.448898196220398, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13113.0546875, "min": 12891.78515625, "max": 43953.77734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29914.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29914.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41426029801368713, "min": -0.1939813792705536, "max": 0.41426029801368713, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.60749816894531, "min": -45.97358703613281, "max": 110.60749816894531, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.26519113779067993, "min": -0.26519113779067993, "max": 0.2595091164112091, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -70.8060302734375, "min": -70.8060302734375, "max": 62.80120849609375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07249231915252483, "min": 0.06485588262158086, "max": 0.07448953349098919, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0148924681353475, "min": 0.5134969463775299, "max": 1.0755207141046415, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02350611888723812, "min": 9.573241595768217e-05, "max": 0.02482281828115167, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3290856644213337, "min": 0.0013402538234075503, "max": 0.3475194559361234, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.315533275807137e-06, "min": 7.315533275807137e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010241746586129991, "min": 0.00010241746586129991, "max": 0.003633872288709299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024384785714286, "min": 0.1024384785714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341387000000003, "min": 1.3886848, "max": 2.6112906999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025360400928571406, "min": 0.00025360400928571406, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003550456129999997, "min": 0.003550456129999997, "max": 0.12114794093000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011065131984651089, "min": 0.010304251685738564, "max": 0.3430934250354767, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1549118459224701, "min": 0.1442595273256302, "max": 2.401654005050659, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 389.67105263157896, "min": 389.67105263157896, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29615.0, "min": 16841.0, "max": 33080.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.481546648144722, "min": -0.9996875515207648, "max": 1.481546648144722, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.11599861085415, "min": -31.990001648664474, "max": 111.11599861085415, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.481546648144722, "min": -0.9996875515207648, "max": 1.481546648144722, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.11599861085415, "min": -31.990001648664474, "max": 111.11599861085415, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044010712603922, "min": 0.044010712603922, "max": 6.1528357880956985, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.30080344529415, "min": 3.1163453327608295, "max": 104.59820839762688, "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": "1758146285", "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": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1758147933" }, "total": 1647.7058888450001, "count": 1, "self": 0.37211878500147577, "children": { "run_training.setup": { "total": 0.024353899999368878, "count": 1, "self": 0.024353899999368878 }, "TrainerController.start_learning": { "total": 1647.3094161599993, "count": 1, "self": 1.2296494608972353, "children": { "TrainerController._reset_env": { "total": 2.1676367999998547, "count": 1, "self": 2.1676367999998547 }, "TrainerController.advance": { "total": 1643.833313979102, "count": 63518, "self": 1.169521133998387, "children": { "env_step": { "total": 1012.973452448995, "count": 63518, "self": 875.4385643982505, "children": { "SubprocessEnvManager._take_step": { "total": 136.8001677479133, "count": 63518, "self": 4.187284010891744, "children": { "TorchPolicy.evaluate": { "total": 132.61288373702155, "count": 62557, "self": 132.61288373702155 } } }, "workers": { "total": 0.7347203028311924, "count": 63518, "self": 0.0, "children": { "worker_root": { "total": 1645.3229921359898, "count": 63518, "is_parallel": true, "self": 856.4614480040118, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002043696999862732, "count": 1, "is_parallel": true, "self": 0.0006568849994437187, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013868120004190132, "count": 8, "is_parallel": true, "self": 0.0013868120004190132 } } }, "UnityEnvironment.step": { "total": 0.03858072099956189, "count": 1, "is_parallel": true, "self": 0.000439674000517698, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003295999995316379, "count": 1, "is_parallel": true, "self": 0.0003295999995316379 }, "communicator.exchange": { "total": 0.03652156899988768, "count": 1, "is_parallel": true, "self": 0.03652156899988768 }, "steps_from_proto": { "total": 0.0012898779996248777, "count": 1, "is_parallel": true, "self": 0.00033262000033573713, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009572579992891406, "count": 8, "is_parallel": true, "self": 0.0009572579992891406 } } } } } } }, "UnityEnvironment.step": { "total": 788.861544131978, "count": 63517, "is_parallel": true, "self": 19.61504065508143, "children": { "UnityEnvironment._generate_step_input": { "total": 13.665959033975014, "count": 63517, "is_parallel": true, "self": 13.665959033975014 }, "communicator.exchange": { "total": 696.1940708950742, "count": 63517, "is_parallel": true, "self": 696.1940708950742 }, "steps_from_proto": { "total": 59.386473547847345, "count": 63517, "is_parallel": true, "self": 12.625899970039427, "children": { "_process_rank_one_or_two_observation": { "total": 46.76057357780792, "count": 508136, "is_parallel": true, "self": 46.76057357780792 } } } } } } } } } } }, "trainer_advance": { "total": 629.6903403961087, "count": 63518, "self": 2.447412737167724, "children": { "process_trajectory": { "total": 116.10428057494664, "count": 63518, "self": 115.91502333394601, "children": { "RLTrainer._checkpoint": { "total": 0.18925724100063235, "count": 2, "self": 0.18925724100063235 } } }, "_update_policy": { "total": 511.13864708399433, "count": 457, "self": 280.1134133019168, "children": { "TorchPPOOptimizer.update": { "total": 231.02523378207752, "count": 22809, "self": 231.02523378207752 } } } } } } }, "trainer_threads": { "total": 1.030000021273736e-06, "count": 1, "self": 1.030000021273736e-06 }, "TrainerController._save_models": { "total": 0.07881489000010333, "count": 1, "self": 0.001300478999837651, "children": { "RLTrainer._checkpoint": { "total": 0.07751441100026568, "count": 1, "self": 0.07751441100026568 } } } } } } }