{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4537639319896698, "min": 0.4537639319896698, "max": 1.3673372268676758, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13714.5615234375, "min": 13714.5615234375, "max": 41479.54296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989994.0, "min": 29952.0, "max": 989994.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5976657867431641, "min": -0.10791371017694473, "max": 0.6335031986236572, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.944091796875, "min": -25.899290084838867, "max": 179.28140258789062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.015805231407284737, "min": -0.015805231407284737, "max": 0.3443756103515625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.441269874572754, "min": -4.441269874572754, "max": 82.650146484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0673594766662323, "min": 0.0651072022031128, "max": 0.072715357330315, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9430326733272523, "min": 0.506749048312402, "max": 1.0702600376292442, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014565963086733108, "min": 0.0001693481555035095, "max": 0.015970475410492128, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2039234832142635, "min": 0.0017263884739837055, "max": 0.22358665574688977, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.61789031787857e-06, "min": 7.61789031787857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010665046445029999, "min": 0.00010665046445029999, "max": 0.0031175821608059994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253926428571432, "min": 0.10253926428571432, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355497000000004, "min": 1.3691136000000002, "max": 2.4001478, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026367250214285714, "min": 0.00026367250214285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00369141503, "min": 0.00369141503, "max": 0.10393548059999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009322361089289188, "min": 0.009322361089289188, "max": 0.47595882415771484, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1305130571126938, "min": 0.1305130571126938, "max": 3.331711769104004, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 339.3804347826087, "min": 303.2783505154639, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31223.0, "min": 15984.0, "max": 34066.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6157260682919752, "min": -1.0000000521540642, "max": 1.695727255910334, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.6467982828617, "min": -32.000001668930054, "max": 167.87699833512306, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6157260682919752, "min": -1.0000000521540642, "max": 1.695727255910334, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.6467982828617, "min": -32.000001668930054, "max": 167.87699833512306, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0328367138800272, "min": 0.030092580188089284, "max": 9.556122034788132, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0209776769625023, "min": 2.913445245809271, "max": 152.8979525566101, "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": "1680008912", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680011108" }, "total": 2195.6978196200002, "count": 1, "self": 0.6909038849998979, "children": { "run_training.setup": { "total": 0.16362891200014928, "count": 1, "self": 0.16362891200014928 }, "TrainerController.start_learning": { "total": 2194.843286823, "count": 1, "self": 1.3975905629840781, "children": { "TrainerController._reset_env": { "total": 7.085317575999852, "count": 1, "self": 7.085317575999852 }, "TrainerController.advance": { "total": 2186.264137563017, "count": 63882, "self": 1.3814049941142912, "children": { "env_step": { "total": 1560.813430597882, "count": 63882, "self": 1453.565284748015, "children": { "SubprocessEnvManager._take_step": { "total": 106.399087346741, "count": 63882, "self": 4.600275104764478, "children": { "TorchPolicy.evaluate": { "total": 101.79881224197652, "count": 62555, "self": 101.79881224197652 } } }, "workers": { "total": 0.8490585031258888, "count": 63882, "self": 0.0, "children": { "worker_root": { "total": 2190.036245876132, "count": 63882, "is_parallel": true, "self": 851.927113911262, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022515549999297946, "count": 1, "is_parallel": true, "self": 0.0006295250000221131, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016220299999076815, "count": 8, "is_parallel": true, "self": 0.0016220299999076815 } } }, "UnityEnvironment.step": { "total": 0.048131857000043965, "count": 1, "is_parallel": true, "self": 0.0005317830004969437, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043582399985098164, "count": 1, "is_parallel": true, "self": 0.00043582399985098164 }, "communicator.exchange": { "total": 0.04541343799974129, "count": 1, "is_parallel": true, "self": 0.04541343799974129 }, "steps_from_proto": { "total": 0.001750811999954749, "count": 1, "is_parallel": true, "self": 0.0003604320008889772, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013903799990657717, "count": 8, "is_parallel": true, "self": 0.0013903799990657717 } } } } } } }, "UnityEnvironment.step": { "total": 1338.10913196487, "count": 63881, "is_parallel": true, "self": 30.72603681404462, "children": { "UnityEnvironment._generate_step_input": { "total": 22.702562970860527, "count": 63881, "is_parallel": true, "self": 22.702562970860527 }, "communicator.exchange": { "total": 1193.9199669830423, "count": 63881, "is_parallel": true, "self": 1193.9199669830423 }, "steps_from_proto": { "total": 90.76056519692247, "count": 63881, "is_parallel": true, "self": 19.194448972039027, "children": { "_process_rank_one_or_two_observation": { "total": 71.56611622488344, "count": 511048, "is_parallel": true, "self": 71.56611622488344 } } } } } } } } } } }, "trainer_advance": { "total": 624.0693019710206, "count": 63882, "self": 2.4629538388803667, "children": { "process_trajectory": { "total": 117.5448049291349, "count": 63882, "self": 117.34824453913416, "children": { "RLTrainer._checkpoint": { "total": 0.19656039000074088, "count": 2, "self": 0.19656039000074088 } } }, "_update_policy": { "total": 504.0615432030054, "count": 437, "self": 322.00474077307535, "children": { "TorchPPOOptimizer.update": { "total": 182.05680242993003, "count": 22800, "self": 182.05680242993003 } } } } } } }, "trainer_threads": { "total": 9.420000424142927e-07, "count": 1, "self": 9.420000424142927e-07 }, "TrainerController._save_models": { "total": 0.09624017899932369, "count": 1, "self": 0.0014051909993213485, "children": { "RLTrainer._checkpoint": { "total": 0.09483498800000234, "count": 1, "self": 0.09483498800000234 } } } } } } }