{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3937203586101532, "min": 0.3937203586101532, "max": 1.4810394048690796, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11956.5, "min": 11702.5244140625, "max": 44928.8125, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5772821307182312, "min": -0.09787259995937347, "max": 0.5936471223831177, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.75259399414062, "min": -23.489423751831055, "max": 166.3851318359375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0050078509375452995, "min": -0.04775834083557129, "max": 0.26908737421035767, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.3771589994430542, "min": -13.085785865783691, "max": 64.85005950927734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0683747396871812, "min": 0.06418858851086245, "max": 0.07410280535136553, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9572463556205368, "min": 0.4644157016611706, "max": 1.0374392749191175, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014894215956388016, "min": 0.0003092251687798487, "max": 0.016319715225974852, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20851902338943223, "min": 0.003659192148551204, "max": 0.2284760131636479, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.353054691871425e-06, "min": 7.353054691871425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010294276568619995, "min": 0.00010294276568619995, "max": 0.0036323779892074, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245098571428571, "min": 0.10245098571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343138, "min": 1.3886848, "max": 2.6107926, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002548534728571428, "min": 0.0002548534728571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003567948619999999, "min": 0.003567948619999999, "max": 0.12109818074000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010130910202860832, "min": 0.010095286183059216, "max": 0.4366183578968048, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14183273911476135, "min": 0.14133401215076447, "max": 3.056328535079956, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 316.95348837209303, "min": 316.95348837209303, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27258.0, "min": 15984.0, "max": 34053.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6153632046162396, "min": -1.0000000521540642, "max": 1.6225097328424454, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 140.53659880161285, "min": -30.999601624906063, "max": 145.76619766652584, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6153632046162396, "min": -1.0000000521540642, "max": 1.6225097328424454, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 140.53659880161285, "min": -30.999601624906063, "max": 145.76619766652584, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03285254710390709, "min": 0.03285254710390709, "max": 8.996293551288545, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8581715980399167, "min": 2.8581715980399167, "max": 143.94069682061672, "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": "1710346616", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/shamekhjr/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710348807" }, "total": 2191.017445169, "count": 1, "self": 0.3712268440003754, "children": { "run_training.setup": { "total": 0.02175253999985216, "count": 1, "self": 0.02175253999985216 }, "TrainerController.start_learning": { "total": 2190.6244657849998, "count": 1, "self": 1.511165009862907, "children": { "TrainerController._reset_env": { "total": 8.88956684699997, "count": 1, "self": 8.88956684699997 }, "TrainerController.advance": { "total": 2180.132325763136, "count": 63859, "self": 1.4556354842297878, "children": { "env_step": { "total": 1436.152933049972, "count": 63859, "self": 1205.2550657919328, "children": { "SubprocessEnvManager._take_step": { "total": 229.83358386806003, "count": 63859, "self": 4.653397392054103, "children": { "TorchPolicy.evaluate": { "total": 225.18018647600593, "count": 62547, "self": 225.18018647600593 } } }, "workers": { "total": 1.0642833899792095, "count": 63859, "self": 0.0, "children": { "worker_root": { "total": 2187.399286959912, "count": 63859, "is_parallel": true, "self": 1083.151272747974, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019703060002029815, "count": 1, "is_parallel": true, "self": 0.0005978110002615722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013724949999414093, "count": 8, "is_parallel": true, "self": 0.0013724949999414093 } } }, "UnityEnvironment.step": { "total": 0.061261038000338885, "count": 1, "is_parallel": true, "self": 0.0007899360002738831, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038503399991896003, "count": 1, "is_parallel": true, "self": 0.00038503399991896003 }, "communicator.exchange": { "total": 0.057137600000260136, "count": 1, "is_parallel": true, "self": 0.057137600000260136 }, "steps_from_proto": { "total": 0.0029484679998859065, "count": 1, "is_parallel": true, "self": 0.0004895979996035749, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024588700002823316, "count": 8, "is_parallel": true, "self": 0.0024588700002823316 } } } } } } }, "UnityEnvironment.step": { "total": 1104.248014211938, "count": 63858, "is_parallel": true, "self": 17.142370606944496, "children": { "UnityEnvironment._generate_step_input": { "total": 11.96076599095295, "count": 63858, "is_parallel": true, "self": 11.96076599095295 }, "communicator.exchange": { "total": 1025.4720243750476, "count": 63858, "is_parallel": true, "self": 1025.4720243750476 }, "steps_from_proto": { "total": 49.67285323899296, "count": 63858, "is_parallel": true, "self": 12.69399583803306, "children": { "_process_rank_one_or_two_observation": { "total": 36.978857400959896, "count": 510864, "is_parallel": true, "self": 36.978857400959896 } } } } } } } } } } }, "trainer_advance": { "total": 742.5237572289343, "count": 63859, "self": 2.832410041033654, "children": { "process_trajectory": { "total": 122.1186972389064, "count": 63859, "self": 121.93534587190607, "children": { "RLTrainer._checkpoint": { "total": 0.18335136700034127, "count": 2, "self": 0.18335136700034127 } } }, "_update_policy": { "total": 617.5726499489942, "count": 454, "self": 247.827777777984, "children": { "TorchPPOOptimizer.update": { "total": 369.74487217101023, "count": 22830, "self": 369.74487217101023 } } } } } } }, "trainer_threads": { "total": 7.560001904494129e-07, "count": 1, "self": 7.560001904494129e-07 }, "TrainerController._save_models": { "total": 0.09140740900056699, "count": 1, "self": 0.0009785840002223267, "children": { "RLTrainer._checkpoint": { "total": 0.09042882500034466, "count": 1, "self": 0.09042882500034466 } } } } } } }