{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4506365656852722, "min": 0.4301571547985077, "max": 1.4723435640335083, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13346.052734375, "min": 12946.009765625, "max": 44665.015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989977.0, "min": 29883.0, "max": 989977.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989977.0, "min": 29883.0, "max": 989977.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44706985354423523, "min": -0.0852995216846466, "max": 0.5319568514823914, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 120.26178741455078, "min": -20.471885681152344, "max": 144.6922607421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017799345776438713, "min": -0.01606505550444126, "max": 0.24433672428131104, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.788023948669434, "min": -4.241174697875977, "max": 59.129486083984375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0670831149431049, "min": 0.06452710820650238, "max": 0.07401372389455955, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0062467241465736, "min": 0.5180960672619169, "max": 1.0326667025025624, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012940356377253518, "min": 0.00041702614363527796, "max": 0.015683270606608686, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19410534565880277, "min": 0.005421339867258614, "max": 0.2195657884925216, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.548697483799997e-06, "min": 7.548697483799997e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011323046225699996, "min": 0.00011323046225699996, "max": 0.0035081804306065995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251619999999997, "min": 0.10251619999999997, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377429999999996, "min": 1.3886848, "max": 2.5693934, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002613683799999999, "min": 0.0002613683799999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003920525699999998, "min": 0.003920525699999998, "max": 0.11696240066000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010470191016793251, "min": 0.010470191016793251, "max": 0.42444613575935364, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15705285966396332, "min": 0.15179023146629333, "max": 2.971122980117798, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 430.69117647058823, "min": 372.61538461538464, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29287.0, "min": 16810.0, "max": 32956.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3918119219701681, "min": -0.9999600519736608, "max": 1.549633308289907, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.25139877200127, "min": -29.998801559209824, "max": 120.87139804661274, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3918119219701681, "min": -0.9999600519736608, "max": 1.549633308289907, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.25139877200127, "min": -29.998801559209824, "max": 120.87139804661274, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04687964050564046, "min": 0.04188277736699465, "max": 7.873247370123863, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.140935913877911, "min": 3.140935913877911, "max": 133.84520529210567, "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": "1767967411", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1767969576" }, "total": 2164.911773074, "count": 1, "self": 0.4842386020000049, "children": { "run_training.setup": { "total": 0.024148526999852038, "count": 1, "self": 0.024148526999852038 }, "TrainerController.start_learning": { "total": 2164.403385945, "count": 1, "self": 1.4689256789938554, "children": { "TrainerController._reset_env": { "total": 2.2612166050000724, "count": 1, "self": 2.2612166050000724 }, "TrainerController.advance": { "total": 2160.595386521006, "count": 63616, "self": 1.46234413302318, "children": { "env_step": { "total": 1500.8253894999832, "count": 63616, "self": 1346.1176546379181, "children": { "SubprocessEnvManager._take_step": { "total": 153.85851863696598, "count": 63616, "self": 4.671780129912577, "children": { "TorchPolicy.evaluate": { "total": 149.1867385070534, "count": 62563, "self": 149.1867385070534 } } }, "workers": { "total": 0.8492162250990987, "count": 63616, "self": 0.0, "children": { "worker_root": { "total": 2157.5198030149663, "count": 63616, "is_parallel": true, "self": 931.066611566989, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017965079998703004, "count": 1, "is_parallel": true, "self": 0.0005891509999855771, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012073569998847233, "count": 8, "is_parallel": true, "self": 0.0012073569998847233 } } }, "UnityEnvironment.step": { "total": 0.05861401700008173, "count": 1, "is_parallel": true, "self": 0.0005402629999480268, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043822300017382076, "count": 1, "is_parallel": true, "self": 0.00043822300017382076 }, "communicator.exchange": { "total": 0.055924718999904144, "count": 1, "is_parallel": true, "self": 0.055924718999904144 }, "steps_from_proto": { "total": 0.0017108120000557392, "count": 1, "is_parallel": true, "self": 0.0003637100005562388, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013471019994995004, "count": 8, "is_parallel": true, "self": 0.0013471019994995004 } } } } } } }, "UnityEnvironment.step": { "total": 1226.4531914479774, "count": 63615, "is_parallel": true, "self": 33.60341632992254, "children": { "UnityEnvironment._generate_step_input": { "total": 22.897310649010024, "count": 63615, "is_parallel": true, "self": 22.897310649010024 }, "communicator.exchange": { "total": 1064.2786051031092, "count": 63615, "is_parallel": true, "self": 1064.2786051031092 }, "steps_from_proto": { "total": 105.67385936593564, "count": 63615, "is_parallel": true, "self": 22.09089908392548, "children": { "_process_rank_one_or_two_observation": { "total": 83.58296028201016, "count": 508920, "is_parallel": true, "self": 83.58296028201016 } } } } } } } } } } }, "trainer_advance": { "total": 658.3076528879992, "count": 63616, "self": 2.802456128857102, "children": { "process_trajectory": { "total": 122.6630907951378, "count": 63616, "self": 122.46348511813744, "children": { "RLTrainer._checkpoint": { "total": 0.19960567700036336, "count": 2, "self": 0.19960567700036336 } } }, "_update_policy": { "total": 532.8421059640043, "count": 451, "self": 295.8816828259776, "children": { "TorchPPOOptimizer.update": { "total": 236.96042313802673, "count": 22752, "self": 236.96042313802673 } } } } } } }, "trainer_threads": { "total": 8.68000370246591e-07, "count": 1, "self": 8.68000370246591e-07 }, "TrainerController._save_models": { "total": 0.07785627199973533, "count": 1, "self": 0.0014498629993795475, "children": { "RLTrainer._checkpoint": { "total": 0.07640640900035578, "count": 1, "self": 0.07640640900035578 } } } } } } }