{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1447216421365738, "min": 0.13826455175876617, "max": 1.4020991325378418, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4311.54736328125, "min": 4110.32861328125, "max": 42534.078125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999906.0, "min": 29952.0, "max": 2999906.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999906.0, "min": 29952.0, "max": 2999906.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8354078531265259, "min": -0.0898745059967041, "max": 0.8648101091384888, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 253.9639892578125, "min": -21.65975570678711, "max": 264.8953857421875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0005675681750290096, "min": -0.035647984594106674, "max": 0.46989473700523376, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.17254072427749634, "min": -10.765690803527832, "max": 111.36505126953125, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06839243630834278, "min": 0.0642259741154822, "max": 0.07358057845950634, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.957494108316799, "min": 0.5010699693236671, "max": 1.0933743211207911, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016001959951522406, "min": 0.00025777547377551656, "max": 0.016716235349858402, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22402743932131366, "min": 0.003608856632857232, "max": 0.2459002963550316, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4866280759190479e-06, "min": 1.4866280759190479e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.081279306286667e-05, "min": 2.081279306286667e-05, "max": 0.0039273246908918, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049550952380955, "min": 0.10049550952380955, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069371333333336, "min": 1.3962282666666668, "max": 2.7674318, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.950140142857143e-05, "min": 5.950140142857143e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008330196200000001, "min": 0.0008330196200000001, "max": 0.13091990918000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007116465829312801, "min": 0.006912874523550272, "max": 0.6042035222053528, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09963051974773407, "min": 0.09678024053573608, "max": 4.229424476623535, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 201.31724137931033, "min": 201.31724137931033, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29191.0, "min": 15984.0, "max": 33183.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7986827498879927, "min": -1.0000000521540642, "max": 1.7986827498879927, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 260.8089987337589, "min": -31.998801663517952, "max": 264.99019791185856, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7986827498879927, "min": -1.0000000521540642, "max": 1.7986827498879927, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 260.8089987337589, "min": -31.998801663517952, "max": 264.99019791185856, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014916455586127744, "min": 0.01485513350705366, "max": 12.990806862711906, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.162886059988523, "min": 2.0054430234522442, "max": 207.8529098033905, "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": "1705861383", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705868597" }, "total": 7214.083407328002, "count": 1, "self": 0.4380659300022671, "children": { "run_training.setup": { "total": 0.05346922899843776, "count": 1, "self": 0.05346922899843776 }, "TrainerController.start_learning": { "total": 7213.591872169001, "count": 1, "self": 4.133439108494713, "children": { "TrainerController._reset_env": { "total": 1.945490416001121, "count": 1, "self": 1.945490416001121 }, "TrainerController.advance": { "total": 7207.428359766509, "count": 194806, "self": 4.374350660815253, "children": { "env_step": { "total": 5307.503929227729, "count": 194806, "self": 4916.2963640494945, "children": { "SubprocessEnvManager._take_step": { "total": 388.60030352147623, "count": 194806, "self": 14.44554687132404, "children": { "TorchPolicy.evaluate": { "total": 374.1547566501522, "count": 187553, "self": 374.1547566501522 } } }, "workers": { "total": 2.6072616567580553, "count": 194806, "self": 0.0, "children": { "worker_root": { "total": 7198.002033440398, "count": 194806, "is_parallel": true, "self": 2652.01298088737, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016610250004305271, "count": 1, "is_parallel": true, "self": 0.0005324970006768126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011285279997537145, "count": 8, "is_parallel": true, "self": 0.0011285279997537145 } } }, "UnityEnvironment.step": { "total": 0.050383321999106556, "count": 1, "is_parallel": true, "self": 0.0006207539972820086, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005093529998703161, "count": 1, "is_parallel": true, "self": 0.0005093529998703161 }, "communicator.exchange": { "total": 0.04745358100080921, "count": 1, "is_parallel": true, "self": 0.04745358100080921 }, "steps_from_proto": { "total": 0.001799634001145023, "count": 1, "is_parallel": true, "self": 0.0003732880013558315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014263459997891914, "count": 8, "is_parallel": true, "self": 0.0014263459997891914 } } } } } } }, "UnityEnvironment.step": { "total": 4545.989052553028, "count": 194805, "is_parallel": true, "self": 106.6345271078826, "children": { "UnityEnvironment._generate_step_input": { "total": 77.94749165817848, "count": 194805, "is_parallel": true, "self": 77.94749165817848 }, "communicator.exchange": { "total": 4051.6340534070277, "count": 194805, "is_parallel": true, "self": 4051.6340534070277 }, "steps_from_proto": { "total": 309.7729803799393, "count": 194805, "is_parallel": true, "self": 63.342609213239484, "children": { "_process_rank_one_or_two_observation": { "total": 246.43037116669984, "count": 1558440, "is_parallel": true, "self": 246.43037116669984 } } } } } } } } } } }, "trainer_advance": { "total": 1895.550079877965, "count": 194806, "self": 8.632492726152122, "children": { "process_trajectory": { "total": 395.10480879086754, "count": 194806, "self": 394.5252831978669, "children": { "RLTrainer._checkpoint": { "total": 0.5795255930006533, "count": 6, "self": 0.5795255930006533 } } }, "_update_policy": { "total": 1491.8127783609452, "count": 1394, "self": 888.6532884770731, "children": { "TorchPPOOptimizer.update": { "total": 603.1594898838721, "count": 68406, "self": 603.1594898838721 } } } } } } }, "trainer_threads": { "total": 8.819988579489291e-07, "count": 1, "self": 8.819988579489291e-07 }, "TrainerController._save_models": { "total": 0.08458199599772342, "count": 1, "self": 0.001658498997130664, "children": { "RLTrainer._checkpoint": { "total": 0.08292349700059276, "count": 1, "self": 0.08292349700059276 } } } } } } }