{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2440253049135208, "min": 0.23376771807670593, "max": 1.4332740306854248, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 7344.185546875, "min": 6975.65576171875, "max": 43479.80078125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999940.0, "min": 29894.0, "max": 2999940.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999940.0, "min": 29894.0, "max": 2999940.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6425041556358337, "min": -0.1000453531742096, "max": 0.7188138365745544, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 183.75619506835938, "min": -24.210975646972656, "max": 211.33126831054688, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012783166021108627, "min": 0.0024774554185569286, "max": 0.4335201382637024, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.6559853553771973, "min": 0.639183521270752, "max": 102.74427032470703, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07072607939545478, "min": 0.06418455095124607, "max": 0.07569079962281866, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0608911909318217, "min": 0.49584554636284933, "max": 1.0980361388064923, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012854261751959308, "min": 6.181097915106983e-05, "max": 0.015670612796975424, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19281392627938962, "min": 0.0008035427289639078, "max": 0.21938857915765592, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5167994944333375e-06, "min": 1.5167994944333375e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2751992416500062e-05, "min": 2.2751992416500062e-05, "max": 0.0038843585052138665, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050556666666667, "min": 0.10050556666666667, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075835, "min": 1.3962282666666668, "max": 2.7674598, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0506110000000156e-05, "min": 6.0506110000000156e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009075916500000023, "min": 0.0009075916500000023, "max": 0.12948913472, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007950177416205406, "min": 0.00752180814743042, "max": 0.6675817370414734, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11925265938043594, "min": 0.10530531406402588, "max": 4.673072338104248, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 304.19607843137254, "min": 266.84684684684686, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31028.0, "min": 16821.0, "max": 34754.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6393553250044295, "min": -0.9999742455059483, "max": 1.7331531421021298, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 168.85359847545624, "min": -30.999201610684395, "max": 195.46319872140884, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6393553250044295, "min": -0.9999742455059483, "max": 1.7331531421021298, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 168.85359847545624, "min": -30.999201610684395, "max": 195.46319872140884, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025506915062472667, "min": 0.022538734765066282, "max": 13.53857048644739, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6272122514346847, "min": 2.3046049775148276, "max": 230.15569826960564, "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": "1674967172", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674973173" }, "total": 6000.912791976, "count": 1, "self": 0.45388145400011126, "children": { "run_training.setup": { "total": 0.10100160199999664, "count": 1, "self": 0.10100160199999664 }, "TrainerController.start_learning": { "total": 6000.35790892, "count": 1, "self": 3.638486817915691, "children": { "TrainerController._reset_env": { "total": 9.521621724000056, "count": 1, "self": 9.521621724000056 }, "TrainerController.advance": { "total": 5987.1050287310845, "count": 192394, "self": 3.6660174333301256, "children": { "env_step": { "total": 4111.829753327829, "count": 192394, "self": 3808.670992488863, "children": { "SubprocessEnvManager._take_step": { "total": 300.99799369695904, "count": 192394, "self": 12.685212644837065, "children": { "TorchPolicy.evaluate": { "total": 288.312781052122, "count": 187570, "self": 98.105148148269, "children": { "TorchPolicy.sample_actions": { "total": 190.20763290385298, "count": 187570, "self": 190.20763290385298 } } } } }, "workers": { "total": 2.1607671420072165, "count": 192394, "self": 0.0, "children": { "worker_root": { "total": 5991.14149980208, "count": 192394, "is_parallel": true, "self": 2463.8379871121915, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006479753000007804, "count": 1, "is_parallel": true, "self": 0.0025029979998407725, "children": { "_process_rank_one_or_two_observation": { "total": 0.0039767550001670315, "count": 8, "is_parallel": true, "self": 0.0039767550001670315 } } }, "UnityEnvironment.step": { "total": 0.047733973000049446, "count": 1, "is_parallel": true, "self": 0.000499989000104506, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000434328999972422, "count": 1, "is_parallel": true, "self": 0.000434328999972422 }, "communicator.exchange": { "total": 0.045147679000024254, "count": 1, "is_parallel": true, "self": 0.045147679000024254 }, "steps_from_proto": { "total": 0.001651975999948263, "count": 1, "is_parallel": true, "self": 0.0004158470001129899, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012361289998352731, "count": 8, "is_parallel": true, "self": 0.0012361289998352731 } } } } } } }, "UnityEnvironment.step": { "total": 3527.3035126898885, "count": 192393, "is_parallel": true, "self": 80.89898877893074, "children": { "UnityEnvironment._generate_step_input": { "total": 64.5051627879593, "count": 192393, "is_parallel": true, "self": 64.5051627879593 }, "communicator.exchange": { "total": 3113.506346699043, "count": 192393, "is_parallel": true, "self": 3113.506346699043 }, "steps_from_proto": { "total": 268.3930144239554, "count": 192393, "is_parallel": true, "self": 63.49734426101986, "children": { "_process_rank_one_or_two_observation": { "total": 204.89567016293552, "count": 1539144, "is_parallel": true, "self": 204.89567016293552 } } } } } } } } } } }, "trainer_advance": { "total": 1871.6092579699252, "count": 192394, "self": 6.774968814665954, "children": { "process_trajectory": { "total": 424.82800199324777, "count": 192394, "self": 424.2723434982478, "children": { "RLTrainer._checkpoint": { "total": 0.5556584949999888, "count": 6, "self": 0.5556584949999888 } } }, "_update_policy": { "total": 1440.0062871620116, "count": 1392, "self": 528.7829494809042, "children": { "TorchPPOOptimizer.update": { "total": 911.2233376811074, "count": 68319, "self": 911.2233376811074 } } } } } } }, "trainer_threads": { "total": 1.026999598252587e-06, "count": 1, "self": 1.026999598252587e-06 }, "TrainerController._save_models": { "total": 0.09277062000001024, "count": 1, "self": 0.0014302359995781444, "children": { "RLTrainer._checkpoint": { "total": 0.0913403840004321, "count": 1, "self": 0.0913403840004321 } } } } } } }