{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17382673919200897, "min": 0.17382673919200897, "max": 1.4680708646774292, "count": 67 }, "Pyramids.Policy.Entropy.sum": { "value": 5245.3955078125, "min": 5245.3955078125, "max": 44535.3984375, "count": 67 }, "Pyramids.Step.mean": { "value": 2009965.0, "min": 29952.0, "max": 2009965.0, "count": 67 }, "Pyramids.Step.sum": { "value": 2009965.0, "min": 29952.0, "max": 2009965.0, "count": 67 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7971019744873047, "min": -0.060563962906599045, "max": 0.838578462600708, "count": 67 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 238.33349609375, "min": -14.595914840698242, "max": 256.6050109863281, "count": 67 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019519036635756493, "min": -0.028085948899388313, "max": 0.44714999198913574, "count": 67 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.8361921310424805, "min": -8.257268905639648, "max": 105.97454833984375, "count": 67 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06736226267466995, "min": 0.06419471886363767, "max": 0.07418490870969392, "count": 67 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9430716774453793, "min": 0.5059105568176039, "max": 1.0986826199040673, "count": 67 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014044906552398383, "min": 0.0006713748298714519, "max": 0.01684946114500151, "count": 67 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19662869173357736, "min": 0.007385123128585971, "max": 0.24235258578019234, "count": 67 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001004180736701881, "min": 0.0001004180736701881, "max": 0.00029838354339596195, "count": 67 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0014058530313826333, "min": 0.0014058530313826333, "max": 0.004162595112468333, "count": 67 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.13347266904761904, "min": 0.13347266904761904, "max": 0.19946118095238097, "count": 67 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.8686173666666666, "min": 1.3962282666666668, "max": 2.887531666666667, "count": 67 }, "Pyramids.Policy.Beta.mean": { "value": 0.0033539196378571424, "min": 0.0033539196378571424, "max": 0.009946171977142856, "count": 67 }, "Pyramids.Policy.Beta.sum": { "value": 0.046954874929999994, "min": 0.046954874929999994, "max": 0.1387644135, "count": 67 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009193127043545246, "min": 0.008977246470749378, "max": 0.5175396800041199, "count": 67 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.128703773021698, "min": 0.12634122371673584, "max": 3.6227777004241943, "count": 67 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 231.1640625, "min": 215.0359712230216, "max": 999.0, "count": 67 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29589.0, "min": 15984.0, "max": 33752.0, "count": 67 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7532062327954918, "min": -1.0000000521540642, "max": 1.7849640184812408, "count": 67 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 224.41039779782295, "min": -30.99840161204338, "max": 248.10999856889248, "count": 67 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7532062327954918, "min": -1.0000000521540642, "max": 1.7849640184812408, "count": 67 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 224.41039779782295, "min": -30.99840161204338, "max": 248.10999856889248, "count": 67 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0218517561149838, "min": 0.02074999827430952, "max": 11.254901316016912, "count": 67 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7970247827179264, "min": 2.6799589603906497, "max": 180.0784210562706, "count": 67 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 67 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1776255384", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./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": "1776258959" }, "total": 3574.305676917, "count": 1, "self": 0.28823517199998605, "children": { "run_training.setup": { "total": 0.020537009000008766, "count": 1, "self": 0.020537009000008766 }, "TrainerController.start_learning": { "total": 3573.996904736, "count": 1, "self": 2.931396191967451, "children": { "TrainerController._reset_env": { "total": 2.424915349999992, "count": 1, "self": 2.424915349999992 }, "TrainerController.advance": { "total": 3568.5578496920325, "count": 131623, "self": 2.761282976023722, "children": { "env_step": { "total": 2259.007255424086, "count": 131623, "self": 1955.863011068092, "children": { "SubprocessEnvManager._take_step": { "total": 301.4284310940611, "count": 131623, "self": 8.978728439078736, "children": { "TorchPolicy.evaluate": { "total": 292.4497026549824, "count": 126698, "self": 292.4497026549824 } } }, "workers": { "total": 1.7158132619330217, "count": 131623, "self": 0.0, "children": { "worker_root": { "total": 3568.7546765180873, "count": 131623, "is_parallel": true, "self": 1800.845883619094, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001861339000015505, "count": 1, "is_parallel": true, "self": 0.0006241529998760598, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012371860001394452, "count": 8, "is_parallel": true, "self": 0.0012371860001394452 } } }, "UnityEnvironment.step": { "total": 0.03911051700004009, "count": 1, "is_parallel": true, "self": 0.00040683100007754547, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030404899996483437, "count": 1, "is_parallel": true, "self": 0.00030404899996483437 }, "communicator.exchange": { "total": 0.03727141000001666, "count": 1, "is_parallel": true, "self": 0.03727141000001666 }, "steps_from_proto": { "total": 0.0011282269999810524, "count": 1, "is_parallel": true, "self": 0.00027942600002006657, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008488009999609858, "count": 8, "is_parallel": true, "self": 0.0008488009999609858 } } } } } } }, "UnityEnvironment.step": { "total": 1767.9087928989934, "count": 131622, "is_parallel": true, "self": 42.61845364200394, "children": { "UnityEnvironment._generate_step_input": { "total": 28.616470887966216, "count": 131622, "is_parallel": true, "self": 28.616470887966216 }, "communicator.exchange": { "total": 1574.5572109919842, "count": 131622, "is_parallel": true, "self": 1574.5572109919842 }, "steps_from_proto": { "total": 122.11665737703902, "count": 131622, "is_parallel": true, "self": 26.733273666144896, "children": { "_process_rank_one_or_two_observation": { "total": 95.38338371089412, "count": 1052976, "is_parallel": true, "self": 95.38338371089412 } } } } } } } } } } }, "trainer_advance": { "total": 1306.7893112919228, "count": 131623, "self": 5.7719391719961095, "children": { "process_trajectory": { "total": 248.87537905092483, "count": 131623, "self": 248.54681763092515, "children": { "RLTrainer._checkpoint": { "total": 0.32856141999968713, "count": 4, "self": 0.32856141999968713 } } }, "_update_policy": { "total": 1052.1419930690017, "count": 942, "self": 569.5711688639472, "children": { "TorchPPOOptimizer.update": { "total": 482.5708242050546, "count": 46133, "self": 482.5708242050546 } } } } } } }, "trainer_threads": { "total": 1.5960004020598717e-06, "count": 1, "self": 1.5960004020598717e-06 }, "TrainerController._save_models": { "total": 0.08274190599968279, "count": 1, "self": 0.0010111109995705192, "children": { "RLTrainer._checkpoint": { "total": 0.08173079500011227, "count": 1, "self": 0.08173079500011227 } } } } } } }