{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39831289649009705, "min": 0.37933555245399475, "max": 1.4144693613052368, "count": 36 }, "Pyramids.Policy.Entropy.sum": { "value": 11923.89453125, "min": 11301.1650390625, "max": 42909.34375, "count": 36 }, "Pyramids.Step.mean": { "value": 1079894.0, "min": 29952.0, "max": 1079894.0, "count": 36 }, "Pyramids.Step.sum": { "value": 1079894.0, "min": 29952.0, "max": 1079894.0, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49702221155166626, "min": -0.14813606441020966, "max": 0.5064069032669067, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 137.17813110351562, "min": -35.70079040527344, "max": 139.1443634033203, "count": 36 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015302793122828007, "min": -0.1931729018688202, "max": 0.7274191379547119, "count": 36 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.223570823669434, "min": -48.872745513916016, "max": 190.5838165283203, "count": 36 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06724070694439838, "min": 0.06536673733498086, "max": 0.07373097220160413, "count": 36 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0086106041659757, "min": 0.505696042935095, "max": 1.076398838687501, "count": 36 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01568846061968038, "min": 0.0006959022423372548, "max": 0.05931613362058071, "count": 36 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2353269092952057, "min": 0.007023961151024996, "max": 0.83042587068813, "count": 36 }, "Pyramids.Policy.LearningRate.mean": { "value": 9.529315005412124e-06, "min": 9.529315005412124e-06, "max": 0.00029559148198898697, "count": 36 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00014293972508118186, "min": 0.00014293972508118186, "max": 0.003572336391039454, "count": 36 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10317640606060606, "min": 0.10317640606060606, "max": 0.19853049350649352, "count": 36 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.547646090909091, "min": 1.3897134545454546, "max": 2.5907787272727276, "count": 36 }, "Pyramids.Policy.Beta.mean": { "value": 0.0003273229654545455, "min": 0.0003273229654545455, "max": 0.009853196301298703, "count": 36 }, "Pyramids.Policy.Beta.sum": { "value": 0.004909844481818182, "min": 0.004909844481818182, "max": 0.11909879485454544, "count": 36 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008349628187716007, "min": 0.008349628187716007, "max": 0.439834326505661, "count": 36 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12524442374706268, "min": 0.11821836233139038, "max": 3.0788402557373047, "count": 36 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 386.0506329113924, "min": 356.29333333333335, "max": 999.0, "count": 36 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30498.0, "min": 15984.0, "max": 32935.0, "count": 36 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5379822618221934, "min": -1.0000000521540642, "max": 1.5917368170462156, "count": 36 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 121.50059868395329, "min": -29.986601628363132, "max": 124.93739838898182, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5379822618221934, "min": -1.0000000521540642, "max": 1.5917368170462156, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 121.50059868395329, "min": -29.986601628363132, "max": 124.93739838898182, "count": 36 }, "Pyramids.Policy.RndReward.mean": { "value": 0.032908780339669104, "min": 0.03172660755387226, "max": 9.193809444084764, "count": 36 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5997936468338594, "min": 2.4112221740942914, "max": 147.10095110535622, "count": 36 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742753822", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742756483" }, "total": 2661.484427951, "count": 1, "self": 0.5429052819999924, "children": { "run_training.setup": { "total": 0.02131256799998482, "count": 1, "self": 0.02131256799998482 }, "TrainerController.start_learning": { "total": 2660.9202101009996, "count": 1, "self": 1.6723123979672891, "children": { "TrainerController._reset_env": { "total": 2.45513235500016, "count": 1, "self": 2.45513235500016 }, "TrainerController.advance": { "total": 2656.6961225780315, "count": 70154, "self": 1.8545058642175718, "children": { "env_step": { "total": 1845.254732636949, "count": 70154, "self": 1662.970226572999, "children": { "SubprocessEnvManager._take_step": { "total": 181.30678605201751, "count": 70154, "self": 5.531262539120462, "children": { "TorchPolicy.evaluate": { "total": 175.77552351289705, "count": 68805, "self": 175.77552351289705 } } }, "workers": { "total": 0.9777200119324334, "count": 70154, "self": 0.0, "children": { "worker_root": { "total": 2654.840841083988, "count": 70154, "is_parallel": true, "self": 1127.9102182590316, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00204206500006876, "count": 1, "is_parallel": true, "self": 0.0006854050006950274, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013566599993737327, "count": 8, "is_parallel": true, "self": 0.0013566599993737327 } } }, "UnityEnvironment.step": { "total": 0.049051121000047715, "count": 1, "is_parallel": true, "self": 0.0006099069998981577, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004437439999946946, "count": 1, "is_parallel": true, "self": 0.0004437439999946946 }, "communicator.exchange": { "total": 0.04632717700019384, "count": 1, "is_parallel": true, "self": 0.04632717700019384 }, "steps_from_proto": { "total": 0.0016702929999610205, "count": 1, "is_parallel": true, "self": 0.00036548799994307046, "children": { "_process_rank_one_or_two_observation": { "total": 0.00130480500001795, "count": 8, "is_parallel": true, "self": 0.00130480500001795 } } } } } } }, "UnityEnvironment.step": { "total": 1526.9306228249563, "count": 70153, "is_parallel": true, "self": 37.96658567590771, "children": { "UnityEnvironment._generate_step_input": { "total": 26.305178255955752, "count": 70153, "is_parallel": true, "self": 26.305178255955752 }, "communicator.exchange": { "total": 1351.4904879181006, "count": 70153, "is_parallel": true, "self": 1351.4904879181006 }, "steps_from_proto": { "total": 111.16837097499229, "count": 70153, "is_parallel": true, "self": 23.053383413983056, "children": { "_process_rank_one_or_two_observation": { "total": 88.11498756100923, "count": 561224, "is_parallel": true, "self": 88.11498756100923 } } } } } } } } } } }, "trainer_advance": { "total": 809.5868840768649, "count": 70154, "self": 3.3277031028792408, "children": { "process_trajectory": { "total": 147.60956463898765, "count": 70154, "self": 147.39496692498778, "children": { "RLTrainer._checkpoint": { "total": 0.21459771399986494, "count": 2, "self": 0.21459771399986494 } } }, "_update_policy": { "total": 658.649616334998, "count": 497, "self": 359.79146385696527, "children": { "TorchPPOOptimizer.update": { "total": 298.8581524780327, "count": 25101, "self": 298.8581524780327 } } } } } } }, "trainer_threads": { "total": 8.919996616896242e-07, "count": 1, "self": 8.919996616896242e-07 }, "TrainerController._save_models": { "total": 0.09664187800080981, "count": 1, "self": 0.0016111670011014212, "children": { "RLTrainer._checkpoint": { "total": 0.09503071099970839, "count": 1, "self": 0.09503071099970839 } } } } } } }