{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15334217250347137, "min": 0.14550833404064178, "max": 1.4580827951431274, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4568.3701171875, "min": 4390.859375, "max": 44232.3984375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999975.0, "min": 29952.0, "max": 2999975.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999975.0, "min": 29952.0, "max": 2999975.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8344985842704773, "min": -0.11472572386264801, "max": 0.93133544921875, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 247.84608459472656, "min": -27.18999671936035, "max": 285.91998291015625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015061009675264359, "min": -0.041735149919986725, "max": 0.47228309512138367, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.473119735717773, "min": -12.395339965820312, "max": 111.93109130859375, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07323107033670467, "min": 0.06316833351558584, "max": 0.07341954434911409, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.09846605505057, "min": 0.5021511376136245, "max": 1.1012931652367113, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01645482676362412, "min": 0.0004983950677887421, "max": 0.017772606112218155, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2468224014543618, "min": 0.006479135881253647, "max": 0.26658909168327233, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5248461584177828e-06, "min": 1.5248461584177828e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2872692376266743e-05, "min": 2.2872692376266743e-05, "max": 0.003982679972440067, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050824888888889, "min": 0.10050824888888889, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5076237333333333, "min": 1.3962282666666668, "max": 2.827559933333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.077406400000019e-05, "min": 6.077406400000019e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009116109600000029, "min": 0.0009116109600000029, "max": 0.13277323734000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0070133269764482975, "min": 0.006790849845856428, "max": 0.540929913520813, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1051999032497406, "min": 0.09507189691066742, "max": 3.7865092754364014, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 232.36363636363637, "min": 194.94771241830065, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30672.0, "min": 15984.0, "max": 32645.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7224318051541394, "min": -1.0000000521540642, "max": 1.8045065652971204, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 227.3609982803464, "min": -30.677001640200615, "max": 281.21599723398685, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7224318051541394, "min": -1.0000000521540642, "max": 1.8045065652971204, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 227.3609982803464, "min": -30.677001640200615, "max": 281.21599723398685, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016842685869271394, "min": 0.014250565705400444, "max": 10.854258147999644, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.223234534743824, "min": 2.091043715001433, "max": 173.6681303679943, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1728524822", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728535092" }, "total": 10270.775925493, "count": 1, "self": 0.8927715089994308, "children": { "run_training.setup": { "total": 0.06843269199998758, "count": 1, "self": 0.06843269199998758 }, "TrainerController.start_learning": { "total": 10269.814721292001, "count": 1, "self": 6.707913922144144, "children": { "TrainerController._reset_env": { "total": 2.6123640730000375, "count": 1, "self": 2.6123640730000375 }, "TrainerController.advance": { "total": 10260.413767875856, "count": 195630, "self": 6.625755845016101, "children": { "env_step": { "total": 7077.287972961012, "count": 195630, "self": 6610.861425282916, "children": { "SubprocessEnvManager._take_step": { "total": 462.3353429199456, "count": 195630, "self": 19.410613271793295, "children": { "TorchPolicy.evaluate": { "total": 442.9247296481523, "count": 187544, "self": 442.9247296481523 } } }, "workers": { "total": 4.091204758150525, "count": 195630, "self": 0.0, "children": { "worker_root": { "total": 10249.457866216022, "count": 195630, "is_parallel": true, "self": 4150.593161048004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002311496000004354, "count": 1, "is_parallel": true, "self": 0.0006854059999454876, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016260900000588663, "count": 8, "is_parallel": true, "self": 0.0016260900000588663 } } }, "UnityEnvironment.step": { "total": 0.05851810000001478, "count": 1, "is_parallel": true, "self": 0.0007406309999851146, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000516025000024456, "count": 1, "is_parallel": true, "self": 0.000516025000024456 }, "communicator.exchange": { "total": 0.055361738999977206, "count": 1, "is_parallel": true, "self": 0.055361738999977206 }, "steps_from_proto": { "total": 0.001899705000028007, "count": 1, "is_parallel": true, "self": 0.0003970410000420088, "children": { "_process_rank_one_or_two_observation": { "total": 0.001502663999985998, "count": 8, "is_parallel": true, "self": 0.001502663999985998 } } } } } } }, "UnityEnvironment.step": { "total": 6098.864705168018, "count": 195629, "is_parallel": true, "self": 143.69912139549615, "children": { "UnityEnvironment._generate_step_input": { "total": 86.9003569751477, "count": 195629, "is_parallel": true, "self": 86.9003569751477 }, "communicator.exchange": { "total": 5491.787630953471, "count": 195629, "is_parallel": true, "self": 5491.787630953471 }, "steps_from_proto": { "total": 376.47759584390315, "count": 195629, "is_parallel": true, "self": 81.79497568267413, "children": { "_process_rank_one_or_two_observation": { "total": 294.682620161229, "count": 1565032, "is_parallel": true, "self": 294.682620161229 } } } } } } } } } } }, "trainer_advance": { "total": 3176.500039069827, "count": 195630, "self": 12.918214511830683, "children": { "process_trajectory": { "total": 489.76103675898077, "count": 195630, "self": 489.18811484598046, "children": { "RLTrainer._checkpoint": { "total": 0.5729219130003003, "count": 6, "self": 0.5729219130003003 } } }, "_update_policy": { "total": 2673.8207877990153, "count": 1394, "self": 1082.7663120329858, "children": { "TorchPPOOptimizer.update": { "total": 1591.0544757660296, "count": 68421, "self": 1591.0544757660296 } } } } } } }, "trainer_threads": { "total": 1.529999281046912e-06, "count": 1, "self": 1.529999281046912e-06 }, "TrainerController._save_models": { "total": 0.08067389100142464, "count": 1, "self": 0.002053626001725206, "children": { "RLTrainer._checkpoint": { "total": 0.07862026499969943, "count": 1, "self": 0.07862026499969943 } } } } } } }