{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3255305290222168, "min": 0.3255305290222168, "max": 1.3856052160263062, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9729.4560546875, "min": 9729.4560546875, "max": 42033.71875, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29990.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29990.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6423845887184143, "min": -0.23765864968299866, "max": 0.6523271799087524, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 186.9339141845703, "min": -56.56275939941406, "max": 186.9339141845703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0125307347625494, "min": 0.0125307347625494, "max": 0.5280995965003967, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.6464438438415527, "min": 3.6464438438415527, "max": 125.68769836425781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06741293461596971, "min": 0.06591779306056976, "max": 0.07355526775801267, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9437810846235759, "min": 0.5711066979555108, "max": 1.071664628747385, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015638514902786397, "min": 0.0012548634557642316, "max": 0.01772017013281584, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21893920863900956, "min": 0.017568088380699242, "max": 0.26580255199223757, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.659204589821429e-06, "min": 7.659204589821429e-06, "max": 0.0002952991515669499, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001072288642575, "min": 0.0001072288642575, "max": 0.0037608316463894997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255303571428571, "min": 0.10255303571428571, "max": 0.19843305, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357425, "min": 1.4357425, "max": 2.6536105000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002650482678571429, "min": 0.0002650482678571429, "max": 0.009843461695, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037106757500000006, "min": 0.0037106757500000006, "max": 0.12537568895000004, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011602463200688362, "min": 0.011602463200688362, "max": 0.6610811352729797, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16243448853492737, "min": 0.16243448853492737, "max": 5.288649082183838, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 294.6181818181818, "min": 294.6181818181818, "max": 991.3125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32408.0, "min": 16661.0, "max": 34536.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6677045738068195, "min": -0.8670750500168651, "max": 1.6677045738068195, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 181.77979854494333, "min": -27.746401600539684, "max": 181.77979854494333, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6677045738068195, "min": -0.8670750500168651, "max": 1.6677045738068195, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 181.77979854494333, "min": -27.746401600539684, "max": 181.77979854494333, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0355441313312515, "min": 0.0355441313312515, "max": 13.948171074776088, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8743103151064133, "min": 3.5152632523095235, "max": 237.1189082711935, "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": "1758101747", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/server/miniconda3/envs/ml-agents/bin/mlagents-learn ./ml-agents/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": "1758102470" }, "total": 723.3812916379975, "count": 1, "self": 0.21678672498092055, "children": { "run_training.setup": { "total": 0.01770655100699514, "count": 1, "self": 0.01770655100699514 }, "TrainerController.start_learning": { "total": 723.1467983620096, "count": 1, "self": 0.7567841245763702, "children": { "TrainerController._reset_env": { "total": 1.1515838979976252, "count": 1, "self": 1.1515838979976252 }, "TrainerController.advance": { "total": 721.2044759904238, "count": 64237, "self": 0.639713269614731, "children": { "env_step": { "total": 473.54191867183545, "count": 64237, "self": 394.74371386626444, "children": { "SubprocessEnvManager._take_step": { "total": 78.30580768972868, "count": 64237, "self": 2.0820459117676364, "children": { "TorchPolicy.evaluate": { "total": 76.22376177796104, "count": 62547, "self": 76.22376177796104 } } }, "workers": { "total": 0.4923971158423228, "count": 64237, "self": 0.0, "children": { "worker_root": { "total": 722.2217306584789, "count": 64237, "is_parallel": true, "self": 371.5010515151953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007574339979328215, "count": 1, "is_parallel": true, "self": 0.0002271339762955904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005303000216372311, "count": 8, "is_parallel": true, "self": 0.0005303000216372311 } } }, "UnityEnvironment.step": { "total": 0.013499919004971161, "count": 1, "is_parallel": true, "self": 0.00014174700481817126, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001304199977312237, "count": 1, "is_parallel": true, "self": 0.0001304199977312237 }, "communicator.exchange": { "total": 0.012843579999753274, "count": 1, "is_parallel": true, "self": 0.012843579999753274 }, "steps_from_proto": { "total": 0.0003841720026684925, "count": 1, "is_parallel": true, "self": 9.385799057781696e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00029031401209067553, "count": 8, "is_parallel": true, "self": 0.00029031401209067553 } } } } } } }, "UnityEnvironment.step": { "total": 350.72067914328363, "count": 64236, "is_parallel": true, "self": 8.787379126166343, "children": { "UnityEnvironment._generate_step_input": { "total": 6.214567223665654, "count": 64236, "is_parallel": true, "self": 6.214567223665654 }, "communicator.exchange": { "total": 309.860906336864, "count": 64236, "is_parallel": true, "self": 309.860906336864 }, "steps_from_proto": { "total": 25.857826456587645, "count": 64236, "is_parallel": true, "self": 6.115064926329069, "children": { "_process_rank_one_or_two_observation": { "total": 19.742761530258576, "count": 513888, "is_parallel": true, "self": 19.742761530258576 } } } } } } } } } } }, "trainer_advance": { "total": 247.02284404897364, "count": 64237, "self": 1.4766023942065658, "children": { "process_trajectory": { "total": 52.63588979464839, "count": 64237, "self": 52.55234069065773, "children": { "RLTrainer._checkpoint": { "total": 0.08354910399066284, "count": 2, "self": 0.08354910399066284 } } }, "_update_policy": { "total": 192.91035186011868, "count": 461, "self": 106.01384408753074, "children": { "TorchPPOOptimizer.update": { "total": 86.89650777258794, "count": 22800, "self": 86.89650777258794 } } } } } } }, "trainer_threads": { "total": 4.2399915400892496e-07, "count": 1, "self": 4.2399915400892496e-07 }, "TrainerController._save_models": { "total": 0.03395392501261085, "count": 1, "self": 0.0009113310079555959, "children": { "RLTrainer._checkpoint": { "total": 0.03304259400465526, "count": 1, "self": 0.03304259400465526 } } } } } } }