{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.546586811542511, "min": 0.546586811542511, "max": 1.5087648630142212, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16423.83984375, "min": 16423.83984375, "max": 45769.890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.22401274740695953, "min": -0.1797155886888504, "max": 0.3843555450439453, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 57.34726333618164, "min": -42.592594146728516, "max": 101.46986389160156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.12566214799880981, "min": -0.1905733048915863, "max": 0.5142925977706909, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -32.16950988769531, "min": -48.40562057495117, "max": 121.8873519897461, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06830019217505608, "min": 0.06470827086691433, "max": 0.07479306248532591, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.956202690450785, "min": 0.4921888544435958, "max": 1.1094337276858734, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014329245110621698, "min": 0.0003881487159051293, "max": 0.02266880760591313, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20060943154870378, "min": 0.0050459333067666805, "max": 0.3173633064827838, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3312189848642875e-06, "min": 7.3312189848642875e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010263706578810002, "min": 0.00010263706578810002, "max": 0.0033822875725709003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244370714285715, "min": 0.10244370714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342119000000002, "min": 1.3691136000000002, "max": 2.5274291000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025412634357142866, "min": 0.00025412634357142866, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003557768810000001, "min": 0.003557768810000001, "max": 0.11277016708999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01158417109400034, "min": 0.01158417109400034, "max": 0.4779216945171356, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1621783971786499, "min": 0.1621783971786499, "max": 3.345451831817627, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 624.9791666666666, "min": 493.9193548387097, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29999.0, "min": 15984.0, "max": 33437.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9165207971818745, "min": -1.0000000521540642, "max": 1.4092741677116962, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 43.99299826472998, "min": -32.000001668930054, "max": 87.37499839812517, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9165207971818745, "min": -1.0000000521540642, "max": 1.4092741677116962, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 43.99299826472998, "min": -32.000001668930054, "max": 87.37499839812517, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07521313768393156, "min": 0.06546724201912331, "max": 10.388796029612422, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.610230608828715, "min": 3.610230608828715, "max": 166.22073647379875, "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": "1719677664", "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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719679746" }, "total": 2082.504979486, "count": 1, "self": 0.857343184000456, "children": { "run_training.setup": { "total": 0.050173782000001665, "count": 1, "self": 0.050173782000001665 }, "TrainerController.start_learning": { "total": 2081.5974625199997, "count": 1, "self": 1.3221122729846684, "children": { "TrainerController._reset_env": { "total": 2.1851363480000146, "count": 1, "self": 2.1851363480000146 }, "TrainerController.advance": { "total": 2077.944856267015, "count": 63401, "self": 1.3716865539345235, "children": { "env_step": { "total": 1449.5456486320109, "count": 63401, "self": 1317.6947315869656, "children": { "SubprocessEnvManager._take_step": { "total": 131.02408240998898, "count": 63401, "self": 4.664802158068824, "children": { "TorchPolicy.evaluate": { "total": 126.35928025192015, "count": 62566, "self": 126.35928025192015 } } }, "workers": { "total": 0.8268346350562297, "count": 63401, "self": 0.0, "children": { "worker_root": { "total": 2076.575412786053, "count": 63401, "is_parallel": true, "self": 879.3150906500468, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020227799998338014, "count": 1, "is_parallel": true, "self": 0.0006171349998567166, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014056449999770848, "count": 8, "is_parallel": true, "self": 0.0014056449999770848 } } }, "UnityEnvironment.step": { "total": 0.05739568599983613, "count": 1, "is_parallel": true, "self": 0.0006244290000267938, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004366609998669446, "count": 1, "is_parallel": true, "self": 0.0004366609998669446 }, "communicator.exchange": { "total": 0.05471404800005075, "count": 1, "is_parallel": true, "self": 0.05471404800005075 }, "steps_from_proto": { "total": 0.0016205479998916417, "count": 1, "is_parallel": true, "self": 0.00034331000006204704, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012772379998295946, "count": 8, "is_parallel": true, "self": 0.0012772379998295946 } } } } } } }, "UnityEnvironment.step": { "total": 1197.2603221360064, "count": 63400, "is_parallel": true, "self": 33.52974719911094, "children": { "UnityEnvironment._generate_step_input": { "total": 23.234317338956544, "count": 63400, "is_parallel": true, "self": 23.234317338956544 }, "communicator.exchange": { "total": 1042.6511677049616, "count": 63400, "is_parallel": true, "self": 1042.6511677049616 }, "steps_from_proto": { "total": 97.84508989297728, "count": 63400, "is_parallel": true, "self": 19.62840045277062, "children": { "_process_rank_one_or_two_observation": { "total": 78.21668944020666, "count": 507200, "is_parallel": true, "self": 78.21668944020666 } } } } } } } } } } }, "trainer_advance": { "total": 627.0275210810698, "count": 63401, "self": 2.5247745370350003, "children": { "process_trajectory": { "total": 123.97192916803897, "count": 63401, "self": 123.66507894403867, "children": { "RLTrainer._checkpoint": { "total": 0.30685022400029993, "count": 2, "self": 0.30685022400029993 } } }, "_update_policy": { "total": 500.53081737599587, "count": 438, "self": 297.34397284799775, "children": { "TorchPPOOptimizer.update": { "total": 203.18684452799812, "count": 22848, "self": 203.18684452799812 } } } } } } }, "trainer_threads": { "total": 1.247000000148546e-06, "count": 1, "self": 1.247000000148546e-06 }, "TrainerController._save_models": { "total": 0.1453563850000137, "count": 1, "self": 0.0020201190000079805, "children": { "RLTrainer._checkpoint": { "total": 0.1433362660000057, "count": 1, "self": 0.1433362660000057 } } } } } } }