{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16060228645801544, "min": 0.15293565392494202, "max": 1.3951654434204102, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4810.35986328125, "min": 4590.35107421875, "max": 42323.73828125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999874.0, "min": 29952.0, "max": 2999874.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999874.0, "min": 29952.0, "max": 2999874.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7418831586837769, "min": -0.1291520744562149, "max": 0.8723424673080444, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 216.6298828125, "min": -30.996498107910156, "max": 265.1921081542969, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.000376074603991583, "min": -0.01018014457076788, "max": 0.4905342757701874, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.10981378704309464, "min": -2.972602128982544, "max": 116.25662231445312, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06725277332670553, "min": 0.0645348647917022, "max": 0.07485331816615785, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9415388265738774, "min": 0.523973227163105, "max": 1.0669906656839885, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015318547058252144, "min": 0.0002519035113252609, "max": 0.01793951728281432, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21445965881553003, "min": 0.0030228421359031307, "max": 0.2663712617621629, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.534020917264287e-06, "min": 1.534020917264287e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.147629284170002e-05, "min": 2.147629284170002e-05, "max": 0.004072412142529333, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051130714285715, "min": 0.10051130714285715, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071583, "min": 1.3962282666666668, "max": 2.857470666666666, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.107958357142861e-05, "min": 6.107958357142861e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008551141700000005, "min": 0.0008551141700000005, "max": 0.1357613196, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005412385333329439, "min": 0.005412385333329439, "max": 0.4234650731086731, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07577339559793472, "min": 0.07577339559793472, "max": 2.9642555713653564, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 256.23478260869564, "min": 217.4609375, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29467.0, "min": 15984.0, "max": 32833.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6915825917668965, "min": -1.0000000521540642, "max": 1.779234835482908, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 194.5319980531931, "min": -30.726801738142967, "max": 241.42199909687042, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6915825917668965, "min": -1.0000000521540642, "max": 1.779234835482908, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 194.5319980531931, "min": -30.726801738142967, "max": 241.42199909687042, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014482669199756144, "min": 0.012643327926866732, "max": 8.803038105368614, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6655069579719566, "min": 1.6183459746389417, "max": 140.84860968589783, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1770659107", "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": "1770666107" }, "total": 6999.541802911999, "count": 1, "self": 0.9211747089993878, "children": { "run_training.setup": { "total": 0.02334239499987234, "count": 1, "self": 0.02334239499987234 }, "TrainerController.start_learning": { "total": 6998.5972858079995, "count": 1, "self": 3.9964553100944613, "children": { "TrainerController._reset_env": { "total": 2.564794283000083, "count": 1, "self": 2.564794283000083 }, "TrainerController.advance": { "total": 6991.918285628905, "count": 194765, "self": 4.094659211486032, "children": { "env_step": { "total": 5057.30200473705, "count": 194765, "self": 4622.499610660345, "children": { "SubprocessEnvManager._take_step": { "total": 432.4372880909168, "count": 194765, "self": 13.50841437802228, "children": { "TorchPolicy.evaluate": { "total": 418.92887371289453, "count": 187562, "self": 418.92887371289453 } } }, "workers": { "total": 2.365105985788432, "count": 194765, "self": 0.0, "children": { "worker_root": { "total": 6979.381409781941, "count": 194765, "is_parallel": true, "self": 2696.1778256648104, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024084140000013576, "count": 1, "is_parallel": true, "self": 0.0006619490000048245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017464649999965332, "count": 8, "is_parallel": true, "self": 0.0017464649999965332 } } }, "UnityEnvironment.step": { "total": 0.10065550399986023, "count": 1, "is_parallel": true, "self": 0.003632759999618429, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004217800001242722, "count": 1, "is_parallel": true, "self": 0.0004217800001242722 }, "communicator.exchange": { "total": 0.09393391699995846, "count": 1, "is_parallel": true, "self": 0.09393391699995846 }, "steps_from_proto": { "total": 0.002667047000159073, "count": 1, "is_parallel": true, "self": 0.0003569450000213692, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023101020001377037, "count": 8, "is_parallel": true, "self": 0.0023101020001377037 } } } } } } }, "UnityEnvironment.step": { "total": 4283.203584117131, "count": 194764, "is_parallel": true, "self": 99.84240218582454, "children": { "UnityEnvironment._generate_step_input": { "total": 67.63112173808395, "count": 194764, "is_parallel": true, "self": 67.63112173808395 }, "communicator.exchange": { "total": 3801.5621461130418, "count": 194764, "is_parallel": true, "self": 3801.5621461130418 }, "steps_from_proto": { "total": 314.16791408018116, "count": 194764, "is_parallel": true, "self": 65.79936822025775, "children": { "_process_rank_one_or_two_observation": { "total": 248.36854585992342, "count": 1558112, "is_parallel": true, "self": 248.36854585992342 } } } } } } } } } } }, "trainer_advance": { "total": 1930.5216216803688, "count": 194765, "self": 7.910686768334017, "children": { "process_trajectory": { "total": 370.42680369602476, "count": 194765, "self": 369.8228249230219, "children": { "RLTrainer._checkpoint": { "total": 0.6039787730028365, "count": 6, "self": 0.6039787730028365 } } }, "_update_policy": { "total": 1552.18413121601, "count": 1399, "self": 855.7651964699808, "children": { "TorchPPOOptimizer.update": { "total": 696.4189347460292, "count": 68355, "self": 696.4189347460292 } } } } } } }, "trainer_threads": { "total": 1.231999704032205e-06, "count": 1, "self": 1.231999704032205e-06 }, "TrainerController._save_models": { "total": 0.11774935399989772, "count": 1, "self": 0.0017111269989982247, "children": { "RLTrainer._checkpoint": { "total": 0.1160382270008995, "count": 1, "self": 0.1160382270008995 } } } } } } }