{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46198317408561707, "min": 0.4535432755947113, "max": 1.4904906749725342, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13933.412109375, "min": 13562.7578125, "max": 45215.5234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6292087435722351, "min": -0.08747809380292892, "max": 0.63307785987854, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.69528198242188, "min": -20.99474334716797, "max": 182.32643127441406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015247449278831482, "min": -0.008729849942028522, "max": 0.30967995524406433, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.330275535583496, "min": -2.426898241043091, "max": 75.5619125366211, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07056572661566039, "min": 0.06360718464649724, "max": 0.07413560038882513, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9879201726192455, "min": 0.5000139551316509, "max": 1.0674033340765163, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0151510875577861, "min": 0.0016794575319610057, "max": 0.0159848475880045, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21211522580900538, "min": 0.021832947915493076, "max": 0.22378786623206298, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.615811747142853e-06, "min": 7.615811747142853e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010662136445999995, "min": 0.00010662136445999995, "max": 0.0036360811879729994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253857142857141, "min": 0.10253857142857141, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355399999999998, "min": 1.3886848, "max": 2.6120270000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026360328571428557, "min": 0.00026360328571428557, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036904459999999983, "min": 0.0036904459999999983, "max": 0.1212214973, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009805873967707157, "min": 0.009664694778621197, "max": 0.4011935591697693, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13728223741054535, "min": 0.1353057324886322, "max": 2.8083548545837402, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 306.2783505154639, "min": 291.22330097087377, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29709.0, "min": 15984.0, "max": 34732.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.694499989401321, "min": -1.0000000521540642, "max": 1.694499989401321, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 166.06099896132946, "min": -26.0912017300725, "max": 173.05879786610603, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.694499989401321, "min": -1.0000000521540642, "max": 1.694499989401321, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 166.06099896132946, "min": -26.0912017300725, "max": 173.05879786610603, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03101782824939749, "min": 0.03092672114200048, "max": 8.079449305310845, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.039747168440954, "min": 2.908477444885648, "max": 129.27118888497353, "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": "1730314037", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.5.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1730315948" }, "total": 1911.9184978460003, "count": 1, "self": 0.32231010000032256, "children": { "run_training.setup": { "total": 0.03868782300014573, "count": 1, "self": 0.03868782300014573 }, "TrainerController.start_learning": { "total": 1911.5574999229998, "count": 1, "self": 1.2058409100063727, "children": { "TrainerController._reset_env": { "total": 2.0504693729999417, "count": 1, "self": 2.0504693729999417 }, "TrainerController.advance": { "total": 1908.247649177994, "count": 64119, "self": 1.1683507070356427, "children": { "env_step": { "total": 1328.1161579150457, "count": 64119, "self": 1233.9228652419815, "children": { "SubprocessEnvManager._take_step": { "total": 93.4869199941204, "count": 64119, "self": 4.370560209089035, "children": { "TorchPolicy.evaluate": { "total": 89.11635978503136, "count": 62560, "self": 89.11635978503136 } } }, "workers": { "total": 0.7063726789438078, "count": 64119, "self": 0.0, "children": { "worker_root": { "total": 1909.381208938958, "count": 64119, "is_parallel": true, "self": 772.8811606898826, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020268600001145387, "count": 1, "is_parallel": true, "self": 0.0006189620003169694, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014078979997975694, "count": 8, "is_parallel": true, "self": 0.0014078979997975694 } } }, "UnityEnvironment.step": { "total": 0.03711682499988456, "count": 1, "is_parallel": true, "self": 0.00041640399967945996, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003119210000477324, "count": 1, "is_parallel": true, "self": 0.0003119210000477324 }, "communicator.exchange": { "total": 0.03534635899995919, "count": 1, "is_parallel": true, "self": 0.03534635899995919 }, "steps_from_proto": { "total": 0.0010421410001981712, "count": 1, "is_parallel": true, "self": 0.00024120600073729292, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008009349994608783, "count": 8, "is_parallel": true, "self": 0.0008009349994608783 } } } } } } }, "UnityEnvironment.step": { "total": 1136.5000482490755, "count": 64118, "is_parallel": true, "self": 20.228414256002452, "children": { "UnityEnvironment._generate_step_input": { "total": 13.311712370005353, "count": 64118, "is_parallel": true, "self": 13.311712370005353 }, "communicator.exchange": { "total": 1046.8678162810306, "count": 64118, "is_parallel": true, "self": 1046.8678162810306 }, "steps_from_proto": { "total": 56.09210534203703, "count": 64118, "is_parallel": true, "self": 12.339824743928602, "children": { "_process_rank_one_or_two_observation": { "total": 43.75228059810843, "count": 512944, "is_parallel": true, "self": 43.75228059810843 } } } } } } } } } } }, "trainer_advance": { "total": 578.9631405559126, "count": 64119, "self": 2.57700773300985, "children": { "process_trajectory": { "total": 115.12597201790004, "count": 64119, "self": 114.97335218190074, "children": { "RLTrainer._checkpoint": { "total": 0.15261983599930318, "count": 2, "self": 0.15261983599930318 } } }, "_update_policy": { "total": 461.26016080500267, "count": 459, "self": 240.31659621301014, "children": { "TorchPPOOptimizer.update": { "total": 220.94356459199253, "count": 22779, "self": 220.94356459199253 } } } } } } }, "trainer_threads": { "total": 8.759998308960348e-07, "count": 1, "self": 8.759998308960348e-07 }, "TrainerController._save_models": { "total": 0.0535395859997152, "count": 1, "self": 0.0013914270002715057, "children": { "RLTrainer._checkpoint": { "total": 0.052148158999443694, "count": 1, "self": 0.052148158999443694 } } } } } } }