{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2540157735347748, "min": 0.2540157735347748, "max": 1.4835628271102905, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7624.537109375, "min": 7624.537109375, "max": 45005.36328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989891.0, "min": 29952.0, "max": 989891.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5873990654945374, "min": -0.09477715194225311, "max": 0.6595998406410217, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 168.58352661132812, "min": -22.841293334960938, "max": 188.6455535888672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012297576293349266, "min": 0.0028042898047715425, "max": 0.3623785078525543, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.529404401779175, "min": 0.7908097505569458, "max": 85.88370513916016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06837319908663632, "min": 0.06611280817638286, "max": 0.07330167926632164, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9572247872129084, "min": 0.5003275706529103, "max": 1.0790865570888855, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017558470736340884, "min": 0.0005560885988112441, "max": 0.017789854377735455, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24581859030877237, "min": 0.0055608859881124415, "max": 0.24905796128829635, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.695568863414284e-06, "min": 7.695568863414284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010773796408779996, "min": 0.00010773796408779996, "max": 0.0035079071306976994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256515714285715, "min": 0.10256515714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359122, "min": 1.3886848, "max": 2.5724969, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026625919857142853, "min": 0.00026625919857142853, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037276287799999997, "min": 0.0037276287799999997, "max": 0.11695329976999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008128086104989052, "min": 0.008128086104989052, "max": 0.3656860291957855, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11379320919513702, "min": 0.11379320919513702, "max": 2.559802293777466, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 301.3980582524272, "min": 292.94117647058823, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31044.0, "min": 15984.0, "max": 32716.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6794807498988051, "min": -1.0000000521540642, "max": 1.6794807498988051, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 174.66599798947573, "min": -30.999001622200012, "max": 174.66599798947573, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6794807498988051, "min": -1.0000000521540642, "max": 1.6794807498988051, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 174.66599798947573, "min": -30.999001622200012, "max": 174.66599798947573, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025117245091958187, "min": 0.025117245091958187, "max": 8.059572318568826, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6121934895636514, "min": 2.494669762905687, "max": 128.9531570971012, "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": "1745817562", "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": "1745820013" }, "total": 2450.688724105, "count": 1, "self": 0.4758423039997979, "children": { "run_training.setup": { "total": 0.02020340799981568, "count": 1, "self": 0.02020340799981568 }, "TrainerController.start_learning": { "total": 2450.1926783930003, "count": 1, "self": 1.5111339850204786, "children": { "TrainerController._reset_env": { "total": 2.3378115949999483, "count": 1, "self": 2.3378115949999483 }, "TrainerController.advance": { "total": 2446.2416730679797, "count": 64189, "self": 1.4937017109741646, "children": { "env_step": { "total": 1742.8044040889815, "count": 64189, "self": 1582.1173790390558, "children": { "SubprocessEnvManager._take_step": { "total": 159.84852614291913, "count": 64189, "self": 4.84631255690897, "children": { "TorchPolicy.evaluate": { "total": 155.00221358601016, "count": 62562, "self": 155.00221358601016 } } }, "workers": { "total": 0.838498907006624, "count": 64189, "self": 0.0, "children": { "worker_root": { "total": 2444.716204789967, "count": 64189, "is_parallel": true, "self": 983.0579283779787, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020849520001320343, "count": 1, "is_parallel": true, "self": 0.0006821910001235665, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014027610000084678, "count": 8, "is_parallel": true, "self": 0.0014027610000084678 } } }, "UnityEnvironment.step": { "total": 0.05239963600001829, "count": 1, "is_parallel": true, "self": 0.0005171259999769973, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004709659999662108, "count": 1, "is_parallel": true, "self": 0.0004709659999662108 }, "communicator.exchange": { "total": 0.04973853899991809, "count": 1, "is_parallel": true, "self": 0.04973853899991809 }, "steps_from_proto": { "total": 0.0016730050001569907, "count": 1, "is_parallel": true, "self": 0.00035630800016406283, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013166969999929279, "count": 8, "is_parallel": true, "self": 0.0013166969999929279 } } } } } } }, "UnityEnvironment.step": { "total": 1461.6582764119883, "count": 64188, "is_parallel": true, "self": 33.228058245054626, "children": { "UnityEnvironment._generate_step_input": { "total": 24.34101606893728, "count": 64188, "is_parallel": true, "self": 24.34101606893728 }, "communicator.exchange": { "total": 1301.203711686958, "count": 64188, "is_parallel": true, "self": 1301.203711686958 }, "steps_from_proto": { "total": 102.88549041103829, "count": 64188, "is_parallel": true, "self": 21.032439808122717, "children": { "_process_rank_one_or_two_observation": { "total": 81.85305060291557, "count": 513504, "is_parallel": true, "self": 81.85305060291557 } } } } } } } } } } }, "trainer_advance": { "total": 701.9435672680238, "count": 64189, "self": 2.74992362310536, "children": { "process_trajectory": { "total": 138.37733344992103, "count": 64189, "self": 138.16415150092098, "children": { "RLTrainer._checkpoint": { "total": 0.21318194900004528, "count": 2, "self": 0.21318194900004528 } } }, "_update_policy": { "total": 560.8163101949974, "count": 450, "self": 310.02154182000845, "children": { "TorchPPOOptimizer.update": { "total": 250.79476837498896, "count": 22833, "self": 250.79476837498896 } } } } } } }, "trainer_threads": { "total": 9.810000847210176e-07, "count": 1, "self": 9.810000847210176e-07 }, "TrainerController._save_models": { "total": 0.10205876400004854, "count": 1, "self": 0.0013659070000358042, "children": { "RLTrainer._checkpoint": { "total": 0.10069285700001274, "count": 1, "self": 0.10069285700001274 } } } } } } }