{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6060996651649475, "min": 0.5907112956047058, "max": 1.486092448234558, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18153.896484375, "min": 17692.984375, "max": 45082.1015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29890.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29890.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.35171371698379517, "min": -0.1112867221236229, "max": 0.361075758934021, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 92.5007095336914, "min": -26.820100784301758, "max": 94.60185241699219, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006738340016454458, "min": -0.007678939029574394, "max": 0.18380391597747803, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.7721834182739258, "min": -1.9504505395889282, "max": 44.29674530029297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06847731417421797, "min": 0.06404659267655491, "max": 0.07321799970719459, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9586823984390517, "min": 0.5570433070082059, "max": 1.0551438969582794, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012433594038187598, "min": 0.00030190667142713053, "max": 0.014001144335534442, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17407031653462637, "min": 0.003622880057125566, "max": 0.21001716503301662, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.515976066135717e-06, "min": 7.515976066135717e-06, "max": 0.000295212826595725, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010522366492590003, "min": 0.00010522366492590003, "max": 0.0035079269306911, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250529285714287, "min": 0.10250529285714287, "max": 0.198404275, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350741000000002, "min": 1.4350741000000002, "max": 2.5693088999999993, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002602787564285715, "min": 0.0002602787564285715, "max": 0.0098405870725, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003643902590000001, "min": 0.003643902590000001, "max": 0.11695395911, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00889782514423132, "min": 0.008669832721352577, "max": 0.41754981875419617, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12456955760717392, "min": 0.12137766182422638, "max": 3.3403985500335693, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 530.1525423728814, "min": 496.4310344827586, "max": 997.7, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31279.0, "min": 16817.0, "max": 33175.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2324847168589042, "min": -0.931880051891009, "max": 1.3061894455499816, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 72.71659829467535, "min": -29.780401691794395, "max": 74.45279839634895, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2324847168589042, "min": -0.931880051891009, "max": 1.3061894455499816, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 72.71659829467535, "min": -29.780401691794395, "max": 74.45279839634895, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.048617039267240106, "min": 0.04643781417137783, "max": 7.865112469476812, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8684053167671664, "min": 2.6027820198214613, "max": 133.7069119811058, "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": "1784124868", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1784128076" }, "total": 3208.4238433960004, "count": 1, "self": 1.236101647000396, "children": { "run_training.setup": { "total": 0.05104732400013745, "count": 1, "self": 0.05104732400013745 }, "TrainerController.start_learning": { "total": 3207.136694425, "count": 1, "self": 2.237718616044276, "children": { "TrainerController._reset_env": { "total": 3.205665206000049, "count": 1, "self": 3.205665206000049 }, "TrainerController.advance": { "total": 3201.5842928099555, "count": 63449, "self": 2.314246574772824, "children": { "env_step": { "total": 2190.3497220899903, "count": 63449, "self": 2039.3842099217995, "children": { "SubprocessEnvManager._take_step": { "total": 149.62845293214605, "count": 63449, "self": 6.530936358129111, "children": { "TorchPolicy.evaluate": { "total": 143.09751657401694, "count": 62570, "self": 143.09751657401694 } } }, "workers": { "total": 1.3370592360447517, "count": 63449, "self": 0.0, "children": { "worker_root": { "total": 3199.4782550110817, "count": 63449, "is_parallel": true, "self": 1337.5271451699732, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0037830410001333803, "count": 1, "is_parallel": true, "self": 0.0013369649996093358, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024460760005240445, "count": 8, "is_parallel": true, "self": 0.0024460760005240445 } } }, "UnityEnvironment.step": { "total": 0.06829251799990743, "count": 1, "is_parallel": true, "self": 0.0006741109996255545, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005237340001258417, "count": 1, "is_parallel": true, "self": 0.0005237340001258417 }, "communicator.exchange": { "total": 0.06503344100019604, "count": 1, "is_parallel": true, "self": 0.06503344100019604 }, "steps_from_proto": { "total": 0.0020612319999600004, "count": 1, "is_parallel": true, "self": 0.0004188999992038589, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016423320007561415, "count": 8, "is_parallel": true, "self": 0.0016423320007561415 } } } } } } }, "UnityEnvironment.step": { "total": 1861.9511098411085, "count": 63448, "is_parallel": true, "self": 44.75702588939703, "children": { "UnityEnvironment._generate_step_input": { "total": 30.29614127687364, "count": 63448, "is_parallel": true, "self": 30.29614127687364 }, "communicator.exchange": { "total": 1647.1733227589602, "count": 63448, "is_parallel": true, "self": 1647.1733227589602 }, "steps_from_proto": { "total": 139.7246199158776, "count": 63448, "is_parallel": true, "self": 27.99728449900931, "children": { "_process_rank_one_or_two_observation": { "total": 111.7273354168683, "count": 507584, "is_parallel": true, "self": 111.7273354168683 } } } } } } } } } } }, "trainer_advance": { "total": 1008.9203241451924, "count": 63449, "self": 4.312693960203433, "children": { "process_trajectory": { "total": 142.01987519998693, "count": 63449, "self": 141.68950227598634, "children": { "RLTrainer._checkpoint": { "total": 0.33037292400058504, "count": 2, "self": 0.33037292400058504 } } }, "_update_policy": { "total": 862.587754985002, "count": 455, "self": 340.7110523009742, "children": { "TorchPPOOptimizer.update": { "total": 521.8767026840278, "count": 22812, "self": 521.8767026840278 } } } } } } }, "trainer_threads": { "total": 1.9170001905877143e-06, "count": 1, "self": 1.9170001905877143e-06 }, "TrainerController._save_models": { "total": 0.10901587599983031, "count": 1, "self": 0.002268539999931818, "children": { "RLTrainer._checkpoint": { "total": 0.1067473359998985, "count": 1, "self": 0.1067473359998985 } } } } } } }