{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4838648736476898, "min": 0.4838648736476898, "max": 1.4665462970733643, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14477.2373046875, "min": 14477.2373046875, "max": 44489.1484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2621012330055237, "min": -0.10959669947624207, "max": 0.29531246423721313, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 68.14632415771484, "min": -26.522401809692383, "max": 76.19061279296875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.21310387551784515, "min": -0.21310387551784515, "max": 0.16509608924388885, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -55.40700912475586, "min": -55.40700912475586, "max": 39.62306213378906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06877254164580628, "min": 0.06499116579445337, "max": 0.07436882542556744, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0315881246870942, "min": 0.4826460013235651, "max": 1.0866282681721107, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.024509305979092486, "min": 0.00045820387225252034, "max": 0.024509305979092486, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.36763958968638727, "min": 0.00502824383553663, "max": 0.36763958968638727, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4777175074600055e-06, "min": 7.4777175074600055e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011216576261190008, "min": 0.00011216576261190008, "max": 0.0032559884146705995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249254000000002, "min": 0.10249254000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373881000000003, "min": 1.3691136000000002, "max": 2.4424676000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002590047460000002, "min": 0.0002590047460000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038850711900000026, "min": 0.0038850711900000026, "max": 0.10855440706000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015293310396373272, "min": 0.015293310396373272, "max": 0.38345977663993835, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2293996512889862, "min": 0.2189958691596985, "max": 2.684218406677246, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 539.0, "min": 526.3157894736842, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29645.0, "min": 15984.0, "max": 32200.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0608836077831008, "min": -1.0000000521540642, "max": 1.1875884306545441, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 58.348598428070545, "min": -32.000001668930054, "max": 65.2923981025815, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0608836077831008, "min": -1.0000000521540642, "max": 1.1875884306545441, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 58.348598428070545, "min": -32.000001668930054, "max": 65.2923981025815, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08562127329324457, "min": 0.08562127329324457, "max": 7.527128459885716, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.709170031128451, "min": 4.709170031128451, "max": 120.43405535817146, "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": "1739289686", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739291818" }, "total": 2131.205614595, "count": 1, "self": 0.47633375300029, "children": { "run_training.setup": { "total": 0.026786995999827923, "count": 1, "self": 0.026786995999827923 }, "TrainerController.start_learning": { "total": 2130.702493846, "count": 1, "self": 1.3896015580526182, "children": { "TrainerController._reset_env": { "total": 2.8163620569998784, "count": 1, "self": 2.8163620569998784 }, "TrainerController.advance": { "total": 2126.413319141947, "count": 63309, "self": 1.3396925199795078, "children": { "env_step": { "total": 1465.46864121297, "count": 63309, "self": 1312.5805394180434, "children": { "SubprocessEnvManager._take_step": { "total": 152.11208044695786, "count": 63309, "self": 4.614198746894999, "children": { "TorchPolicy.evaluate": { "total": 147.49788170006286, "count": 62560, "self": 147.49788170006286 } } }, "workers": { "total": 0.7760213479687081, "count": 63309, "self": 0.0, "children": { "worker_root": { "total": 2125.896955140065, "count": 63309, "is_parallel": true, "self": 924.8897796610295, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002505911999833188, "count": 1, "is_parallel": true, "self": 0.000709716999608645, "children": { "_process_rank_one_or_two_observation": { "total": 0.001796195000224543, "count": 8, "is_parallel": true, "self": 0.001796195000224543 } } }, "UnityEnvironment.step": { "total": 0.05030596200003856, "count": 1, "is_parallel": true, "self": 0.0005773769998995704, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004838549998567032, "count": 1, "is_parallel": true, "self": 0.0004838549998567032 }, "communicator.exchange": { "total": 0.04755826000018715, "count": 1, "is_parallel": true, "self": 0.04755826000018715 }, "steps_from_proto": { "total": 0.0016864700000951416, "count": 1, "is_parallel": true, "self": 0.00036456700081544113, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013219029992797005, "count": 8, "is_parallel": true, "self": 0.0013219029992797005 } } } } } } }, "UnityEnvironment.step": { "total": 1201.0071754790356, "count": 63308, "is_parallel": true, "self": 31.29904010510336, "children": { "UnityEnvironment._generate_step_input": { "total": 22.83572746888558, "count": 63308, "is_parallel": true, "self": 22.83572746888558 }, "communicator.exchange": { "total": 1051.1390867750588, "count": 63308, "is_parallel": true, "self": 1051.1390867750588 }, "steps_from_proto": { "total": 95.73332112998787, "count": 63308, "is_parallel": true, "self": 19.43761818490475, "children": { "_process_rank_one_or_two_observation": { "total": 76.29570294508312, "count": 506464, "is_parallel": true, "self": 76.29570294508312 } } } } } } } } } } }, "trainer_advance": { "total": 659.6049854089974, "count": 63309, "self": 2.5848510510313645, "children": { "process_trajectory": { "total": 123.43533769595751, "count": 63309, "self": 123.13094273395791, "children": { "RLTrainer._checkpoint": { "total": 0.3043949619996056, "count": 2, "self": 0.3043949619996056 } } }, "_update_policy": { "total": 533.5847966620086, "count": 444, "self": 292.38386045596917, "children": { "TorchPPOOptimizer.update": { "total": 241.2009362060394, "count": 22848, "self": 241.2009362060394 } } } } } } }, "trainer_threads": { "total": 7.500002539018169e-07, "count": 1, "self": 7.500002539018169e-07 }, "TrainerController._save_models": { "total": 0.08321033900028851, "count": 1, "self": 0.0014210680001269793, "children": { "RLTrainer._checkpoint": { "total": 0.08178927100016153, "count": 1, "self": 0.08178927100016153 } } } } } } }