{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3126651644706726, "min": 0.3126651644706726, "max": 1.4830652475357056, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9439.986328125, "min": 9439.986328125, "max": 44990.265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6440969109535217, "min": -0.11517664790153503, "max": 0.6667439341545105, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.92352294921875, "min": -27.64239501953125, "max": 196.689453125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.021574661135673523, "min": -0.011081111617386341, "max": 0.19272860884666443, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.127203941345215, "min": -2.9919002056121826, "max": 46.447593688964844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06865724720083977, "min": 0.06491629725011687, "max": 0.07425822704862593, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9612014608117567, "min": 0.46425254144451594, "max": 1.0655170901776656, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017079490964656045, "min": 0.0005111907352456266, "max": 0.017751928120214002, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23911287350518465, "min": 0.005623098087701893, "max": 0.24852699368299605, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.577604617021424e-06, "min": 7.577604617021424e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010608646463829994, "min": 0.00010608646463829994, "max": 0.0033774611741797006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252583571428571, "min": 0.10252583571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353616999999999, "min": 1.3886848, "max": 2.5724635000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026233098785714284, "min": 0.00026233098785714284, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036726338299999995, "min": 0.0036726338299999995, "max": 0.11260944796999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012415140867233276, "min": 0.01229994185268879, "max": 0.30774956941604614, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17381197214126587, "min": 0.17219918966293335, "max": 2.1542470455169678, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 296.03, "min": 268.35087719298247, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29603.0, "min": 15984.0, "max": 33603.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6706605923898292, "min": -1.0000000521540642, "max": 1.6965543681330848, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 165.3953986465931, "min": -31.997201651334763, "max": 193.40719796717167, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6706605923898292, "min": -1.0000000521540642, "max": 1.6965543681330848, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 165.3953986465931, "min": -31.997201651334763, "max": 193.40719796717167, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03695177683829285, "min": 0.03478887279223336, "max": 5.5431052101776, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6582259069909924, "min": 3.6582259069909924, "max": 88.6896833628416, "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": "1730903001", "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+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730905395" }, "total": 2393.8100320070002, "count": 1, "self": 0.47620706000043356, "children": { "run_training.setup": { "total": 0.059727465000008806, "count": 1, "self": 0.059727465000008806 }, "TrainerController.start_learning": { "total": 2393.274097482, "count": 1, "self": 1.5373563599600857, "children": { "TrainerController._reset_env": { "total": 5.094628470999993, "count": 1, "self": 5.094628470999993 }, "TrainerController.advance": { "total": 2386.55588698604, "count": 64086, "self": 1.6032670800336746, "children": { "env_step": { "total": 1679.5679471389883, "count": 64086, "self": 1515.3957405899723, "children": { "SubprocessEnvManager._take_step": { "total": 163.24835823000006, "count": 64086, "self": 4.962359318995311, "children": { "TorchPolicy.evaluate": { "total": 158.28599891100475, "count": 62543, "self": 158.28599891100475 } } }, "workers": { "total": 0.9238483190159457, "count": 64086, "self": 0.0, "children": { "worker_root": { "total": 2387.583288950981, "count": 64086, "is_parallel": true, "self": 998.7859691859705, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023132110000005923, "count": 1, "is_parallel": true, "self": 0.0007255310000289228, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015876799999716695, "count": 8, "is_parallel": true, "self": 0.0015876799999716695 } } }, "UnityEnvironment.step": { "total": 0.04868450600000074, "count": 1, "is_parallel": true, "self": 0.0006750439999905211, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004383659999973588, "count": 1, "is_parallel": true, "self": 0.0004383659999973588 }, "communicator.exchange": { "total": 0.04556087000000275, "count": 1, "is_parallel": true, "self": 0.04556087000000275 }, "steps_from_proto": { "total": 0.002010226000010107, "count": 1, "is_parallel": true, "self": 0.00047611300001904056, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015341129999910663, "count": 8, "is_parallel": true, "self": 0.0015341129999910663 } } } } } } }, "UnityEnvironment.step": { "total": 1388.7973197650106, "count": 64085, "is_parallel": true, "self": 35.210078186021065, "children": { "UnityEnvironment._generate_step_input": { "total": 24.175421144974678, "count": 64085, "is_parallel": true, "self": 24.175421144974678 }, "communicator.exchange": { "total": 1225.509682474988, "count": 64085, "is_parallel": true, "self": 1225.509682474988 }, "steps_from_proto": { "total": 103.90213795902682, "count": 64085, "is_parallel": true, "self": 21.711122956068635, "children": { "_process_rank_one_or_two_observation": { "total": 82.19101500295818, "count": 512680, "is_parallel": true, "self": 82.19101500295818 } } } } } } } } } } }, "trainer_advance": { "total": 705.384672767018, "count": 64086, "self": 2.943763530010642, "children": { "process_trajectory": { "total": 140.17337908700952, "count": 64086, "self": 139.92001211700963, "children": { "RLTrainer._checkpoint": { "total": 0.25336696999988817, "count": 2, "self": 0.25336696999988817 } } }, "_update_policy": { "total": 562.2675301499978, "count": 451, "self": 314.7967977820134, "children": { "TorchPPOOptimizer.update": { "total": 247.4707323679844, "count": 22845, "self": 247.4707323679844 } } } } } } }, "trainer_threads": { "total": 8.940000952861737e-07, "count": 1, "self": 8.940000952861737e-07 }, "TrainerController._save_models": { "total": 0.08622477099970638, "count": 1, "self": 0.0014417689994843386, "children": { "RLTrainer._checkpoint": { "total": 0.08478300200022204, "count": 1, "self": 0.08478300200022204 } } } } } } }