{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3886653780937195, "min": 0.3886653780937195, "max": 1.48847496509552, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11821.646484375, "min": 11821.646484375, "max": 45154.375, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5604120492935181, "min": -0.27312779426574707, "max": 0.6007319688796997, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 156.91537475585938, "min": -64.73128509521484, "max": 168.2049560546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022871237248182297, "min": -0.03366792947053909, "max": 0.19346365332603455, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.403946399688721, "min": -9.292348861694336, "max": 46.62474060058594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06925965592520134, "min": 0.0660663541258102, "max": 0.07321228132267214, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9696351829528187, "min": 0.5075589953294497, "max": 1.0663296644052023, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01610296498672271, "min": 0.0021425522801248797, "max": 0.017292298195700693, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22544150981411798, "min": 0.02731902868918487, "max": 0.24209217473980968, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.538518915764291e-06, "min": 7.538518915764291e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010553926482070008, "min": 0.00010553926482070008, "max": 0.0035087876304041995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251280714285715, "min": 0.10251280714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351793000000002, "min": 1.3886848, "max": 2.617957, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026102943357142873, "min": 0.00026102943357142873, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003654412070000002, "min": 0.003654412070000002, "max": 0.11698262041999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009437923319637775, "min": 0.008843580260872841, "max": 0.3118534982204437, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1321309208869934, "min": 0.1300508975982666, "max": 2.1829745769500732, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 343.82105263157894, "min": 298.3030303030303, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32663.0, "min": 15984.0, "max": 33292.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5496999803692737, "min": -1.0000000521540642, "max": 1.661278772685263, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 145.67179815471172, "min": -27.3230018094182, "max": 164.46659849584103, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5496999803692737, "min": -1.0000000521540642, "max": 1.661278772685263, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 145.67179815471172, "min": -27.3230018094182, "max": 164.46659849584103, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03318444501441108, "min": 0.028758911434749162, "max": 6.161439008079469, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.119337831354642, "min": 2.8140907826600596, "max": 98.58302412927151, "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": "1711105616", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "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": "1711107903" }, "total": 2287.444130099, "count": 1, "self": 0.526343903000452, "children": { "run_training.setup": { "total": 0.08420583099996293, "count": 1, "self": 0.08420583099996293 }, "TrainerController.start_learning": { "total": 2286.8335803649998, "count": 1, "self": 1.4539740188997712, "children": { "TrainerController._reset_env": { "total": 2.337443857999915, "count": 1, "self": 2.337443857999915 }, "TrainerController.advance": { "total": 2282.955220387101, "count": 63985, "self": 1.446988678141679, "children": { "env_step": { "total": 1631.9518841929905, "count": 63985, "self": 1496.2179924859836, "children": { "SubprocessEnvManager._take_step": { "total": 134.8574191769685, "count": 63985, "self": 4.807125874956455, "children": { "TorchPolicy.evaluate": { "total": 130.05029330201205, "count": 62551, "self": 130.05029330201205 } } }, "workers": { "total": 0.8764725300384271, "count": 63985, "self": 0.0, "children": { "worker_root": { "total": 2281.666616679987, "count": 63985, "is_parallel": true, "self": 909.0536149240004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023957529999734106, "count": 1, "is_parallel": true, "self": 0.0006842439997853944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017115090001880162, "count": 8, "is_parallel": true, "self": 0.0017115090001880162 } } }, "UnityEnvironment.step": { "total": 0.04806105999978172, "count": 1, "is_parallel": true, "self": 0.0006680279998363403, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005008379998798773, "count": 1, "is_parallel": true, "self": 0.0005008379998798773 }, "communicator.exchange": { "total": 0.04517311600011453, "count": 1, "is_parallel": true, "self": 0.04517311600011453 }, "steps_from_proto": { "total": 0.0017190779999509687, "count": 1, "is_parallel": true, "self": 0.00035946899993177794, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013596090000191907, "count": 8, "is_parallel": true, "self": 0.0013596090000191907 } } } } } } }, "UnityEnvironment.step": { "total": 1372.6130017559865, "count": 63984, "is_parallel": true, "self": 37.300765591091476, "children": { "UnityEnvironment._generate_step_input": { "total": 25.182592151006475, "count": 63984, "is_parallel": true, "self": 25.182592151006475 }, "communicator.exchange": { "total": 1205.0046438919512, "count": 63984, "is_parallel": true, "self": 1205.0046438919512 }, "steps_from_proto": { "total": 105.12500012193732, "count": 63984, "is_parallel": true, "self": 21.260655753850187, "children": { "_process_rank_one_or_two_observation": { "total": 83.86434436808713, "count": 511872, "is_parallel": true, "self": 83.86434436808713 } } } } } } } } } } }, "trainer_advance": { "total": 649.5563475159688, "count": 63985, "self": 2.7685868209907767, "children": { "process_trajectory": { "total": 130.115908119981, "count": 63985, "self": 129.90787601798024, "children": { "RLTrainer._checkpoint": { "total": 0.20803210200074318, "count": 2, "self": 0.20803210200074318 } } }, "_update_policy": { "total": 516.671852574997, "count": 455, "self": 303.46967882100444, "children": { "TorchPPOOptimizer.update": { "total": 213.2021737539926, "count": 22794, "self": 213.2021737539926 } } } } } } }, "trainer_threads": { "total": 9.429995770915411e-07, "count": 1, "self": 9.429995770915411e-07 }, "TrainerController._save_models": { "total": 0.08694115799971769, "count": 1, "self": 0.001489010999648599, "children": { "RLTrainer._checkpoint": { "total": 0.08545214700006909, "count": 1, "self": 0.08545214700006909 } } } } } } }