{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17238448560237885, "min": 0.17238448560237885, "max": 0.4386698603630066, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 5168.7763671875, "min": 5168.7763671875, "max": 13279.4140625, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 239.1344537815126, "min": 233.21875, "max": 434.5890410958904, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28457.0, "min": 26486.0, "max": 32147.0, "count": 50 }, "Pyramids.Step.mean": { "value": 2999888.0, "min": 1529917.0, "max": 2999888.0, "count": 50 }, "Pyramids.Step.sum": { "value": 2999888.0, "min": 1529917.0, "max": 2999888.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7131645679473877, "min": 0.4455733299255371, "max": 0.796072244644165, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 206.1045684814453, "min": 119.41365051269531, "max": 238.02560424804688, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.014351245947182178, "min": -0.014351245947182178, "max": 0.04299667850136757, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.147510051727295, "min": -4.147510051727295, "max": 12.254053115844727, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7441649939864874, "min": 1.452405525578393, "max": 1.765361516406903, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 209.2997992783785, "min": 104.57319784164429, "max": 229.49699713289738, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7441649939864874, "min": 1.452405525578393, "max": 1.765361516406903, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 209.2997992783785, "min": 104.57319784164429, "max": 229.49699713289738, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017248182781289263, "min": 0.016540855615575906, "max": 0.030271496027833363, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0697819337547116, "min": 1.9187392514068051, "max": 2.631578191911103, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06890699563969281, "min": 0.0641046498323897, "max": 0.07349883796026309, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9646979389556993, "min": 0.8974650976534558, "max": 1.0898302044952288, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014523039718845946, "min": 0.011826284802395686, "max": 0.016752761555835605, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20332255606384325, "min": 0.1655679872335396, "max": 0.25129142333753407, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4912566458047617e-06, "min": 1.4912566458047617e-06, "max": 0.00014841503624262383, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0877593041266665e-05, "min": 2.0877593041266665e-05, "max": 0.002077810507396734, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049705238095238, "min": 0.10049705238095238, "max": 0.14947166190476188, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069587333333333, "min": 1.4069587333333333, "max": 2.167489933333333, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 5.9655532857142854e-05, "min": 5.9655532857142854e-05, "max": 0.004952219024285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.00083517746, "min": 0.00083517746, "max": 0.06933106634, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006828543730080128, "min": 0.006670892238616943, "max": 0.008476497605443, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09559961408376694, "min": 0.09355184435844421, "max": 0.1255975365638733, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1721577486", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/montana/miniconda3/envs/huggy/bin/mlagents-learn ./config/ppo/Pyramids_monti-python.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --resume", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1721581194" }, "total": 3708.2879716539996, "count": 1, "self": 3.5138402890002, "children": { "run_training.setup": { "total": 0.020744760000070528, "count": 1, "self": 0.020744760000070528 }, "TrainerController.start_learning": { "total": 3704.7533866049994, "count": 1, "self": 2.2625416599294113, "children": { "TrainerController._reset_env": { "total": 6.4037488269996174, "count": 1, "self": 6.4037488269996174 }, "TrainerController.advance": { "total": 3695.9654878380693, "count": 98056, "self": 2.155551096081581, "children": { "env_step": { "total": 2311.4620702199873, "count": 98056, "self": 1861.5856962680955, "children": { "SubprocessEnvManager._take_step": { "total": 448.33788196998785, "count": 98056, "self": 7.739947279845637, "children": { "TorchPolicy.evaluate": { "total": 440.5979346901422, "count": 93817, "self": 440.5979346901422 } } }, "workers": { "total": 1.538491981903917, "count": 98056, "self": 0.0, "children": { "worker_root": { "total": 3699.826716139885, "count": 98056, "is_parallel": true, "self": 1991.0893479278552, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027083519998996053, "count": 1, "is_parallel": true, "self": 0.001124918999721558, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015834330001780472, "count": 8, "is_parallel": true, "self": 0.0015834330001780472 } } }, "UnityEnvironment.step": { "total": 0.18151721000003818, "count": 1, "is_parallel": true, "self": 0.000799858999926073, "children": { "UnityEnvironment._generate_step_input": { "total": 0.01702640900020924, "count": 1, "is_parallel": true, "self": 0.01702640900020924 }, "communicator.exchange": { "total": 0.15682314700006827, "count": 1, "is_parallel": true, "self": 0.15682314700006827 }, "steps_from_proto": { "total": 0.006867794999834587, "count": 1, "is_parallel": true, "self": 0.0024335269999937736, "children": { "_process_rank_one_or_two_observation": { "total": 0.004434267999840813, "count": 8, "is_parallel": true, "self": 0.004434267999840813 } } } } } } }, "UnityEnvironment.step": { "total": 1708.7373682120297, "count": 98055, "is_parallel": true, "self": 24.673811604014645, "children": { "UnityEnvironment._generate_step_input": { "total": 17.454303040972263, "count": 98055, "is_parallel": true, "self": 17.454303040972263 }, "communicator.exchange": { "total": 1592.8492911650587, "count": 98055, "is_parallel": true, "self": 1592.8492911650587 }, "steps_from_proto": { "total": 73.75996240198401, "count": 98055, "is_parallel": true, "self": 18.674706146530298, "children": { "_process_rank_one_or_two_observation": { "total": 55.085256255453714, "count": 784440, "is_parallel": true, "self": 55.085256255453714 } } } } } } } } } } }, "trainer_advance": { "total": 1382.3478665220005, "count": 98056, "self": 4.842771278079454, "children": { "process_trajectory": { "total": 239.89799281390697, "count": 98056, "self": 237.71325387890647, "children": { "RLTrainer._checkpoint": { "total": 2.184738935000496, "count": 15, "self": 2.184738935000496 } } }, "_update_policy": { "total": 1137.607102430014, "count": 709, "self": 525.0799924310904, "children": { "TorchPPOOptimizer.update": { "total": 612.5271099989236, "count": 34098, "self": 612.5271099989236 } } } } } } }, "trainer_threads": { "total": 7.040007403702475e-07, "count": 1, "self": 7.040007403702475e-07 }, "TrainerController._save_models": { "total": 0.12160757600031502, "count": 1, "self": 0.0030337309999595163, "children": { "RLTrainer._checkpoint": { "total": 0.1185738450003555, "count": 1, "self": 0.1185738450003555 } } } } } } }