{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6906391978263855, "min": 0.6906391978263855, "max": 1.4951658248901367, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20730.2265625, "min": 20730.2265625, "max": 45357.3515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.27455276250839233, "min": -0.11421945691108704, "max": 0.3237708806991577, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 70.83460998535156, "min": -27.52688980102539, "max": 84.50419616699219, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02057463303208351, "min": 0.0064631132408976555, "max": 0.29000282287597656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.308255195617676, "min": 1.6868726015090942, "max": 68.73066711425781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06699241352826052, "min": 0.0656680480939903, "max": 0.07335828341116818, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0048862029239078, "min": 0.46529204374341154, "max": 1.1003742511675227, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00920045412552343, "min": 0.0003991615375175802, "max": 0.011246829549712683, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13800681188285147, "min": 0.0035924538376582217, "max": 0.1630658896707852, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.477417507560001e-06, "min": 7.477417507560001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011216126261340002, "min": 0.00011216126261340002, "max": 0.0032538758153748, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249244, "min": 0.10249244, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373866, "min": 1.3886848, "max": 2.5274535000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025899475600000014, "min": 0.00025899475600000014, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003884921340000002, "min": 0.003884921340000002, "max": 0.10848405748000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009754347614943981, "min": 0.009754347614943981, "max": 0.2952248156070709, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14631521701812744, "min": 0.13918960094451904, "max": 2.0665736198425293, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 574.7058823529412, "min": 501.08620689655174, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29310.0, "min": 15984.0, "max": 32064.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.010996133662187, "min": -1.0000000521540642, "max": 1.2574551498581623, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 52.57179895043373, "min": -31.99920167028904, "max": 72.93239869177341, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.010996133662187, "min": -1.0000000521540642, "max": 1.2574551498581623, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 52.57179895043373, "min": -31.99920167028904, "max": 72.93239869177341, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05742890287505221, "min": 0.05648217876421705, "max": 5.640241575893015, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.986302949502715, "min": 2.986302949502715, "max": 90.24386521428823, "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": "1707091623", "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 Training 3 --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": "1707093642" }, "total": 2019.2278016229998, "count": 1, "self": 0.4919788150000386, "children": { "run_training.setup": { "total": 0.04893460799996774, "count": 1, "self": 0.04893460799996774 }, "TrainerController.start_learning": { "total": 2018.6868881999999, "count": 1, "self": 1.3881859550233457, "children": { "TrainerController._reset_env": { "total": 3.5434164409999767, "count": 1, "self": 3.5434164409999767 }, "TrainerController.advance": { "total": 2013.6664307699762, "count": 63323, "self": 1.4140257250232935, "children": { "env_step": { "total": 1401.5376707810005, "count": 63323, "self": 1267.18659548997, "children": { "SubprocessEnvManager._take_step": { "total": 133.49414123700717, "count": 63323, "self": 4.765669864033725, "children": { "TorchPolicy.evaluate": { "total": 128.72847137297344, "count": 62565, "self": 128.72847137297344 } } }, "workers": { "total": 0.8569340540234407, "count": 63323, "self": 0.0, "children": { "worker_root": { "total": 2013.5183327320265, "count": 63323, "is_parallel": true, "self": 863.6075987310046, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005404927999961728, "count": 1, "is_parallel": true, "self": 0.0035062549999338444, "children": { "_process_rank_one_or_two_observation": { "total": 0.001898673000027884, "count": 8, "is_parallel": true, "self": 0.001898673000027884 } } }, "UnityEnvironment.step": { "total": 0.06259626900009607, "count": 1, "is_parallel": true, "self": 0.0006871919999866805, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005273060000945407, "count": 1, "is_parallel": true, "self": 0.0005273060000945407 }, "communicator.exchange": { "total": 0.05953579100003026, "count": 1, "is_parallel": true, "self": 0.05953579100003026 }, "steps_from_proto": { "total": 0.0018459799999845927, "count": 1, "is_parallel": true, "self": 0.00037511799996536865, "children": { "_process_rank_one_or_two_observation": { "total": 0.001470862000019224, "count": 8, "is_parallel": true, "self": 0.001470862000019224 } } } } } } }, "UnityEnvironment.step": { "total": 1149.9107340010219, "count": 63322, "is_parallel": true, "self": 35.72028183412158, "children": { "UnityEnvironment._generate_step_input": { "total": 25.723027451930875, "count": 63322, "is_parallel": true, "self": 25.723027451930875 }, "communicator.exchange": { "total": 987.1775453110225, "count": 63322, "is_parallel": true, "self": 987.1775453110225 }, "steps_from_proto": { "total": 101.28987940394677, "count": 63322, "is_parallel": true, "self": 20.37958872600234, "children": { "_process_rank_one_or_two_observation": { "total": 80.91029067794443, "count": 506576, "is_parallel": true, "self": 80.91029067794443 } } } } } } } } } } }, "trainer_advance": { "total": 610.7147342639523, "count": 63323, "self": 2.6287915809639344, "children": { "process_trajectory": { "total": 123.11211411799331, "count": 63323, "self": 122.91227023899341, "children": { "RLTrainer._checkpoint": { "total": 0.19984387899989997, "count": 2, "self": 0.19984387899989997 } } }, "_update_policy": { "total": 484.9738285649951, "count": 443, "self": 284.1170614180311, "children": { "TorchPPOOptimizer.update": { "total": 200.856767146964, "count": 22794, "self": 200.856767146964 } } } } } } }, "trainer_threads": { "total": 1.6080002751550637e-06, "count": 1, "self": 1.6080002751550637e-06 }, "TrainerController._save_models": { "total": 0.0888534260002416, "count": 1, "self": 0.0013717900001211092, "children": { "RLTrainer._checkpoint": { "total": 0.08748163600012049, "count": 1, "self": 0.08748163600012049 } } } } } } }