{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4989413917064667, "min": 0.4989413917064667, "max": 1.4293795824050903, "count": 20 }, "Pyramids.Policy.Entropy.sum": { "value": 24923.12109375, "min": 24923.12109375, "max": 73344.328125, "count": 20 }, "Pyramids.Step.mean": { "value": 999994.0, "min": 49999.0, "max": 999994.0, "count": 20 }, "Pyramids.Step.sum": { "value": 999994.0, "min": 49999.0, "max": 999994.0, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44722381234169006, "min": -0.15053996443748474, "max": 0.4697890281677246, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 203.03961181640625, "min": -60.21598434448242, "max": 208.58633422851562, "count": 20 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004529879428446293, "min": -0.029852984473109245, "max": 0.21218928694725037, "count": 20 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.056565284729004, "min": -13.403989791870117, "max": 84.87571716308594, "count": 20 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07023798171842655, "min": 0.06651402399575973, "max": 0.07223996628962083, "count": 20 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.685711561242237, "min": 1.0642243839321557, "max": 1.70845932859811, "count": 20 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01557881709973741, "min": 0.00042453183367450526, "max": 0.015704640767378604, "count": 20 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.37389161039369784, "min": 0.006792509338792084, "max": 0.3769113784170865, "count": 20 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2400618353229172e-05, "min": 1.2400618353229172e-05, "max": 0.00048591980281603996, "count": 20 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0002976148404775001, "min": 0.0002976148404775001, "max": 0.0086648378670325, "count": 20 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10372015625000001, "min": 0.10372015625000001, "max": 0.24577594000000003, "count": 20 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.4892837500000002, "min": 2.4892837500000002, "max": 4.69945125, "count": 20 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005057728229166669, "min": 0.0005057728229166669, "max": 0.019437073604000005, "count": 20 }, "Pyramids.Policy.Beta.sum": { "value": 0.012138547750000006, "min": 0.012138547750000006, "max": 0.34663020325, "count": 20 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007374455686658621, "min": 0.007374455686658621, "max": 0.23428532481193542, "count": 20 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1769869327545166, "min": 0.1769869327545166, "max": 3.514279842376709, "count": 20 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 396.5238095238095, "min": 396.5238095238095, "max": 998.0816326530612, "count": 20 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 49962.0, "min": 47391.0, "max": 52985.0, "count": 20 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5240809309577186, "min": -0.9581265819011903, "max": 1.5242427203517694, "count": 20 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 192.03419730067253, "min": -47.32480262219906, "max": 192.03419730067253, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5240809309577186, "min": -0.9581265819011903, "max": 1.5242427203517694, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 192.03419730067253, "min": -47.32480262219906, "max": 192.03419730067253, "count": 20 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03005820108753849, "min": 0.03005820108753849, "max": 3.453037386139234, "count": 20 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7873333370298496, "min": 3.7873333370298496, "max": 165.74579453468323, "count": 20 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1754260147", "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 Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754262199" }, "total": 2051.925213308, "count": 1, "self": 0.48042967400033376, "children": { "run_training.setup": { "total": 0.020772050999994462, "count": 1, "self": 0.020772050999994462 }, "TrainerController.start_learning": { "total": 2051.424011583, "count": 1, "self": 1.2068278359820397, "children": { "TrainerController._reset_env": { "total": 2.242998132000139, "count": 1, "self": 2.242998132000139 }, "TrainerController.advance": { "total": 2047.9211100040172, "count": 63521, "self": 1.2852512751583163, "children": { "env_step": { "total": 1389.0082914509653, "count": 63521, "self": 1248.0789007198614, "children": { "SubprocessEnvManager._take_step": { "total": 140.18443809208156, "count": 63521, "self": 4.332620591086425, "children": { "TorchPolicy.evaluate": { "total": 135.85181750099514, "count": 62555, "self": 135.85181750099514 } } }, "workers": { "total": 0.7449526390223582, "count": 63521, "self": 0.0, "children": { "worker_root": { "total": 2046.7786512479688, "count": 63521, "is_parallel": true, "self": 904.3168658719696, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019231500000387314, "count": 1, "is_parallel": true, "self": 0.0006253590006508603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012977909993878711, "count": 8, "is_parallel": true, "self": 0.0012977909993878711 } } }, "UnityEnvironment.step": { "total": 0.048935672999959934, "count": 1, "is_parallel": true, "self": 0.0005640179999772954, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004631140000128653, "count": 1, "is_parallel": true, "self": 0.0004631140000128653 }, "communicator.exchange": { "total": 0.046270800000002055, "count": 1, "is_parallel": true, "self": 0.046270800000002055 }, "steps_from_proto": { "total": 0.0016377409999677184, "count": 1, "is_parallel": true, "self": 0.0003543450002325699, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012833959997351485, "count": 8, "is_parallel": true, "self": 0.0012833959997351485 } } } } } } }, "UnityEnvironment.step": { "total": 1142.4617853759992, "count": 63520, "is_parallel": true, "self": 31.38029533891995, "children": { "UnityEnvironment._generate_step_input": { "total": 22.350248200067426, "count": 63520, "is_parallel": true, "self": 22.350248200067426 }, "communicator.exchange": { "total": 996.3066306639548, "count": 63520, "is_parallel": true, "self": 996.3066306639548 }, "steps_from_proto": { "total": 92.42461117305697, "count": 63520, "is_parallel": true, "self": 18.166856267967887, "children": { "_process_rank_one_or_two_observation": { "total": 74.25775490508909, "count": 508160, "is_parallel": true, "self": 74.25775490508909 } } } } } } } } } } }, "trainer_advance": { "total": 657.6275672778936, "count": 63521, "self": 2.293590928902404, "children": { "process_trajectory": { "total": 121.70594015698998, "count": 63521, "self": 121.52243338598964, "children": { "RLTrainer._checkpoint": { "total": 0.18350677100033863, "count": 2, "self": 0.18350677100033863 } } }, "_update_policy": { "total": 533.6280361920012, "count": 444, "self": 299.0185733919534, "children": { "TorchPPOOptimizer.update": { "total": 234.60946280004782, "count": 22848, "self": 234.60946280004782 } } } } } } }, "trainer_threads": { "total": 8.910001270123757e-07, "count": 1, "self": 8.910001270123757e-07 }, "TrainerController._save_models": { "total": 0.05307472000004054, "count": 1, "self": 0.0006058310000298661, "children": { "RLTrainer._checkpoint": { "total": 0.05246888900001068, "count": 1, "self": 0.05246888900001068 } } } } } } }