{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2678722143173218, "min": 0.2678722143173218, "max": 1.4566599130630493, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8070.4541015625, "min": 8070.4541015625, "max": 44189.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6088693141937256, "min": -0.18862010538578033, "max": 0.6651120781898499, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 175.3543701171875, "min": -44.702964782714844, "max": 186.23138427734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.012935866601765156, "min": -0.021185407415032387, "max": 0.6679487824440002, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.725529670715332, "min": -5.953099250793457, "max": 158.30386352539062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06736297140568717, "min": 0.06345748721908782, "max": 0.07228599398293833, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9430815996796204, "min": 0.49581849172774267, "max": 1.0245875643621032, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017005834190058525, "min": 0.0009502981991765142, "max": 0.019869962226157188, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23808167866081933, "min": 0.012353876589294684, "max": 0.262017256094088, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.375897541400001e-06, "min": 7.375897541400001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010326256557960001, "min": 0.00010326256557960001, "max": 0.0035050625316459, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024586, "min": 0.1024586, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344204, "min": 1.3886848, "max": 2.5683541, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002556141400000001, "min": 0.0002556141400000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035785979600000007, "min": 0.0035785979600000007, "max": 0.11685857459, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009519731625914574, "min": 0.009519731625914574, "max": 0.6429498791694641, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13327623903751373, "min": 0.13327623903751373, "max": 4.5006489753723145, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 319.09183673469386, "min": 291.3904761904762, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31271.0, "min": 15984.0, "max": 32729.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6829999877948953, "min": -1.0000000521540642, "max": 1.6829999877948953, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 166.61699879169464, "min": -30.761001750826836, "max": 173.40279795229435, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6829999877948953, "min": -1.0000000521540642, "max": 1.6829999877948953, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 166.61699879169464, "min": -30.761001750826836, "max": 173.40279795229435, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031203257944787656, "min": 0.030037391420122923, "max": 15.03150775283575, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.089122536533978, "min": 2.8535521849116776, "max": 240.504124045372, "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": "1710887595", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710889932" }, "total": 2336.344029688, "count": 1, "self": 0.48269102399990516, "children": { "run_training.setup": { "total": 0.05389572900003259, "count": 1, "self": 0.05389572900003259 }, "TrainerController.start_learning": { "total": 2335.807442935, "count": 1, "self": 1.489488417029861, "children": { "TrainerController._reset_env": { "total": 2.9867930720001823, "count": 1, "self": 2.9867930720001823 }, "TrainerController.advance": { "total": 2331.2309838319693, "count": 64157, "self": 1.5397990739934357, "children": { "env_step": { "total": 1691.6551948100255, "count": 64157, "self": 1553.1894216499577, "children": { "SubprocessEnvManager._take_step": { "total": 137.55792267203674, "count": 64157, "self": 4.942103169029224, "children": { "TorchPolicy.evaluate": { "total": 132.61581950300751, "count": 62545, "self": 132.61581950300751 } } }, "workers": { "total": 0.9078504880310447, "count": 64157, "self": 0.0, "children": { "worker_root": { "total": 2330.469335139055, "count": 64157, "is_parallel": true, "self": 903.7131034410527, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008345226000074035, "count": 1, "is_parallel": true, "self": 0.0069358400003238785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014093859997501568, "count": 8, "is_parallel": true, "self": 0.0014093859997501568 } } }, "UnityEnvironment.step": { "total": 0.07968623099986871, "count": 1, "is_parallel": true, "self": 0.0007147310000163998, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004919709999740007, "count": 1, "is_parallel": true, "self": 0.0004919709999740007 }, "communicator.exchange": { "total": 0.07620416800000385, "count": 1, "is_parallel": true, "self": 0.07620416800000385 }, "steps_from_proto": { "total": 0.002275360999874465, "count": 1, "is_parallel": true, "self": 0.0004423189996032306, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018330420002712344, "count": 8, "is_parallel": true, "self": 0.0018330420002712344 } } } } } } }, "UnityEnvironment.step": { "total": 1426.7562316980025, "count": 64156, "is_parallel": true, "self": 35.67072886201777, "children": { "UnityEnvironment._generate_step_input": { "total": 25.783994810968352, "count": 64156, "is_parallel": true, "self": 25.783994810968352 }, "communicator.exchange": { "total": 1257.388255018028, "count": 64156, "is_parallel": true, "self": 1257.388255018028 }, "steps_from_proto": { "total": 107.91325300698827, "count": 64156, "is_parallel": true, "self": 22.17540061691193, "children": { "_process_rank_one_or_two_observation": { "total": 85.73785239007634, "count": 513248, "is_parallel": true, "self": 85.73785239007634 } } } } } } } } } } }, "trainer_advance": { "total": 638.0359899479504, "count": 64157, "self": 2.9007766990084747, "children": { "process_trajectory": { "total": 135.77889996094382, "count": 64157, "self": 135.4471136869438, "children": { "RLTrainer._checkpoint": { "total": 0.3317862740000237, "count": 2, "self": 0.3317862740000237 } } }, "_update_policy": { "total": 499.3563132879981, "count": 454, "self": 290.8576266810021, "children": { "TorchPPOOptimizer.update": { "total": 208.498686606996, "count": 22830, "self": 208.498686606996 } } } } } } }, "trainer_threads": { "total": 1.1890001587744337e-06, "count": 1, "self": 1.1890001587744337e-06 }, "TrainerController._save_models": { "total": 0.10017642500042712, "count": 1, "self": 0.001507030000539089, "children": { "RLTrainer._checkpoint": { "total": 0.09866939499988803, "count": 1, "self": 0.09866939499988803 } } } } } } }