{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47236329317092896, "min": 0.458514928817749, "max": 1.4433969259262085, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14170.8984375, "min": 13740.775390625, "max": 43786.890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989920.0, "min": 29952.0, "max": 989920.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36124733090400696, "min": -0.09892983734607697, "max": 0.48307329416275024, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 95.36929321289062, "min": -23.842090606689453, "max": 131.39593505859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.042085569351911545, "min": -0.012892386876046658, "max": 0.25710371136665344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.110589981079102, "min": -3.2102043628692627, "max": 61.70488739013672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06801222333380808, "min": 0.06588454707387081, "max": 0.07389297727172374, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.952171126673313, "min": 0.49904678346175735, "max": 1.0642044619501878, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01306504421921725, "min": 0.0005778326679845515, "max": 0.01478731196749279, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1829106190690415, "min": 0.0072803072817470985, "max": 0.20702236754489906, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.53245463207143e-06, "min": 7.53245463207143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010545436484900002, "min": 0.00010545436484900002, "max": 0.0035082539305821, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251078571428573, "min": 0.10251078571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351510000000003, "min": 1.3691136000000002, "max": 2.5694179, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002608274928571429, "min": 0.0002608274928571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036515849000000006, "min": 0.0036515849000000006, "max": 0.11696484820999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0095343217253685, "min": 0.009474159218370914, "max": 0.4751955568790436, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.133480504155159, "min": 0.13263823091983795, "max": 3.326368808746338, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 452.2985074626866, "min": 372.3703703703704, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30304.0, "min": 15984.0, "max": 33547.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2491313183485573, "min": -1.0000000521540642, "max": 1.5025874801911414, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 83.69179832935333, "min": -32.000001668930054, "max": 120.20699841529131, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2491313183485573, "min": -1.0000000521540642, "max": 1.5025874801911414, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 83.69179832935333, "min": -32.000001668930054, "max": 120.20699841529131, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04458860680765, "min": 0.03814346618655691, "max": 10.327977978624403, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.98743665611255, "min": 2.98743665611255, "max": 165.24764765799046, "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": "1707230779", "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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707232928" }, "total": 2149.007663271, "count": 1, "self": 0.4754602240004715, "children": { "run_training.setup": { "total": 0.05280319700000291, "count": 1, "self": 0.05280319700000291 }, "TrainerController.start_learning": { "total": 2148.47939985, "count": 1, "self": 1.4350300560631695, "children": { "TrainerController._reset_env": { "total": 2.260260745999858, "count": 1, "self": 2.260260745999858 }, "TrainerController.advance": { "total": 2144.7024454939365, "count": 63584, "self": 1.504322958908233, "children": { "env_step": { "total": 1508.8654234179921, "count": 63584, "self": 1372.0094006500444, "children": { "SubprocessEnvManager._take_step": { "total": 135.94531190199837, "count": 63584, "self": 4.9240982810104015, "children": { "TorchPolicy.evaluate": { "total": 131.02121362098796, "count": 62560, "self": 131.02121362098796 } } }, "workers": { "total": 0.9107108659493406, "count": 63584, "self": 0.0, "children": { "worker_root": { "total": 2143.132666595949, "count": 63584, "is_parallel": true, "self": 894.5170995329568, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021812039999531407, "count": 1, "is_parallel": true, "self": 0.0007308100000500417, "children": { "_process_rank_one_or_two_observation": { "total": 0.001450393999903099, "count": 8, "is_parallel": true, "self": 0.001450393999903099 } } }, "UnityEnvironment.step": { "total": 0.06653976599977796, "count": 1, "is_parallel": true, "self": 0.0007478269997136522, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005077109999547247, "count": 1, "is_parallel": true, "self": 0.0005077109999547247 }, "communicator.exchange": { "total": 0.0561459420000574, "count": 1, "is_parallel": true, "self": 0.0561459420000574 }, "steps_from_proto": { "total": 0.009138286000052176, "count": 1, "is_parallel": true, "self": 0.007717351999644961, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014209340004072146, "count": 8, "is_parallel": true, "self": 0.0014209340004072146 } } } } } } }, "UnityEnvironment.step": { "total": 1248.6155670629923, "count": 63583, "is_parallel": true, "self": 35.372986165820066, "children": { "UnityEnvironment._generate_step_input": { "total": 25.497567582085594, "count": 63583, "is_parallel": true, "self": 25.497567582085594 }, "communicator.exchange": { "total": 1083.9063331300792, "count": 63583, "is_parallel": true, "self": 1083.9063331300792 }, "steps_from_proto": { "total": 103.83868018500743, "count": 63583, "is_parallel": true, "self": 21.106822948028366, "children": { "_process_rank_one_or_two_observation": { "total": 82.73185723697907, "count": 508664, "is_parallel": true, "self": 82.73185723697907 } } } } } } } } } } }, "trainer_advance": { "total": 634.3326991170359, "count": 63584, "self": 2.726089176970845, "children": { "process_trajectory": { "total": 128.34972294206045, "count": 63584, "self": 128.15297425206063, "children": { "RLTrainer._checkpoint": { "total": 0.1967486899998221, "count": 2, "self": 0.1967486899998221 } } }, "_update_policy": { "total": 503.2568869980046, "count": 447, "self": 295.7731463640348, "children": { "TorchPPOOptimizer.update": { "total": 207.48374063396977, "count": 22830, "self": 207.48374063396977 } } } } } } }, "trainer_threads": { "total": 9.61000296229031e-07, "count": 1, "self": 9.61000296229031e-07 }, "TrainerController._save_models": { "total": 0.08166259300014644, "count": 1, "self": 0.0013443729999380594, "children": { "RLTrainer._checkpoint": { "total": 0.08031822000020838, "count": 1, "self": 0.08031822000020838 } } } } } } }