{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36977726221084595, "min": 0.3580505847930908, "max": 1.450472116470337, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11146.5654296875, "min": 10730.0595703125, "max": 44001.5234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989959.0, "min": 29910.0, "max": 989959.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989959.0, "min": 29910.0, "max": 989959.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.511104941368103, "min": -0.09569025784730911, "max": 0.511104941368103, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.02053833007812, "min": -23.061351776123047, "max": 140.27413940429688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0028107797261327505, "min": -0.0028107797261327505, "max": 0.3171139061450958, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.7645320892333984, "min": -0.7645320892333984, "max": 76.21006774902344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06836471756280585, "min": 0.06690948150935583, "max": 0.07832613427867526, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9571060458792819, "min": 0.5482829399507267, "max": 1.0661902121906215, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016924253872428442, "min": 0.000883372145429386, "max": 0.017694441992803366, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23693955421399818, "min": 0.011483837890582018, "max": 0.2477221878992471, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.690918864964284e-06, "min": 7.690918864964284e-06, "max": 0.0002952347158741428, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010767286410949997, "min": 0.00010767286410949997, "max": 0.003608931997022699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256360714285714, "min": 0.10256360714285714, "max": 0.19841157142857144, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358905, "min": 1.388881, "max": 2.5281195, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026610435357142856, "min": 0.00026610435357142856, "max": 0.009841315985714286, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037254609499999996, "min": 0.0037254609499999996, "max": 0.12030743227, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007130883634090424, "min": 0.007130883634090424, "max": 0.5126622915267944, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09983237087726593, "min": 0.09983237087726593, "max": 3.5886359214782715, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 374.6666666666667, "min": 346.1025641025641, "max": 996.96875, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32596.0, "min": 16709.0, "max": 32758.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5551883494264858, "min": -0.9352375506423414, "max": 1.5769512663858058, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 133.74619805067778, "min": -29.927601620554924, "max": 133.74619805067778, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5551883494264858, "min": -0.9352375506423414, "max": 1.5769512663858058, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 133.74619805067778, "min": -29.927601620554924, "max": 133.74619805067778, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028216918677614115, "min": 0.028216918677614115, "max": 10.193550705909729, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.426655006274814, "min": 2.2230944259572425, "max": 173.2903620004654, "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": "1740969635", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [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", "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": "1740972709" }, "total": 3073.866505559, "count": 1, "self": 0.6370618709997871, "children": { "run_training.setup": { "total": 0.051447962000565894, "count": 1, "self": 0.051447962000565894 }, "TrainerController.start_learning": { "total": 3073.1779957259996, "count": 1, "self": 2.323609612995824, "children": { "TrainerController._reset_env": { "total": 5.540949600000204, "count": 1, "self": 5.540949600000204 }, "TrainerController.advance": { "total": 3065.2258622980034, "count": 63935, "self": 2.4867665199499243, "children": { "env_step": { "total": 2038.6802913680858, "count": 63935, "self": 1879.7043428387487, "children": { "SubprocessEnvManager._take_step": { "total": 157.55149409516343, "count": 63935, "self": 6.526093197179762, "children": { "TorchPolicy.evaluate": { "total": 151.02540089798367, "count": 62572, "self": 151.02540089798367 } } }, "workers": { "total": 1.42445443417364, "count": 63935, "self": 0.0, "children": { "worker_root": { "total": 3066.2177714231775, "count": 63935, "is_parallel": true, "self": 1353.0819421951646, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007856244000322476, "count": 1, "is_parallel": true, "self": 0.004865047999373928, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029911960009485483, "count": 8, "is_parallel": true, "self": 0.0029911960009485483 } } }, "UnityEnvironment.step": { "total": 0.2623013610000271, "count": 1, "is_parallel": true, "self": 0.0044218780003575375, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006978009996601031, "count": 1, "is_parallel": true, "self": 0.0006978009996601031 }, "communicator.exchange": { "total": 0.24702279200027988, "count": 1, "is_parallel": true, "self": 0.24702279200027988 }, "steps_from_proto": { "total": 0.010158889999729581, "count": 1, "is_parallel": true, "self": 0.0027321899997332366, "children": { "_process_rank_one_or_two_observation": { "total": 0.0074266999999963446, "count": 8, "is_parallel": true, "self": 0.0074266999999963446 } } } } } } }, "UnityEnvironment.step": { "total": 1713.1358292280129, "count": 63934, "is_parallel": true, "self": 45.48663933717489, "children": { "UnityEnvironment._generate_step_input": { "total": 30.03815249996751, "count": 63934, "is_parallel": true, "self": 30.03815249996751 }, "communicator.exchange": { "total": 1509.0095357108576, "count": 63934, "is_parallel": true, "self": 1509.0095357108576 }, "steps_from_proto": { "total": 128.60150168001292, "count": 63934, "is_parallel": true, "self": 27.371362279034656, "children": { "_process_rank_one_or_two_observation": { "total": 101.23013940097826, "count": 511472, "is_parallel": true, "self": 101.23013940097826 } } } } } } } } } } }, "trainer_advance": { "total": 1024.0588044099677, "count": 63935, "self": 4.656121496868764, "children": { "process_trajectory": { "total": 155.849403922095, "count": 63935, "self": 155.41898029609547, "children": { "RLTrainer._checkpoint": { "total": 0.43042362599953776, "count": 2, "self": 0.43042362599953776 } } }, "_update_policy": { "total": 863.5532789910039, "count": 457, "self": 354.14338129989756, "children": { "TorchPPOOptimizer.update": { "total": 509.4098976911064, "count": 22788, "self": 509.4098976911064 } } } } } } }, "trainer_threads": { "total": 1.0430003385408781e-06, "count": 1, "self": 1.0430003385408781e-06 }, "TrainerController._save_models": { "total": 0.08757317199979298, "count": 1, "self": 0.0019128180001644068, "children": { "RLTrainer._checkpoint": { "total": 0.08566035399962857, "count": 1, "self": 0.08566035399962857 } } } } } } }