{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3763675093650818, "min": 0.3763675093650818, "max": 1.4210846424102783, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11363.2880859375, "min": 11363.2880859375, "max": 43110.0234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29968.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29968.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6796466708183289, "min": -0.1025855541229248, "max": 0.6796466708183289, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 195.05859375, "min": -24.415361404418945, "max": 197.69992065429688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007846272550523281, "min": -0.0020385959651321173, "max": 0.3995338976383209, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.251880168914795, "min": -0.5850770473480225, "max": 95.08906555175781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06855923893227657, "min": 0.06569562162854219, "max": 0.0741296376275358, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0283885839841485, "min": 0.5508339137945285, "max": 1.0574741578905151, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016659822768350645, "min": 0.0007297723761805036, "max": 0.016659822768350645, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2498973415252597, "min": 0.008757268514166043, "max": 0.2498973415252597, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4557175147933355e-06, "min": 7.4557175147933355e-06, "max": 0.0002948526017158, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011183576272190003, "min": 0.00011183576272190003, "max": 0.003510369229877, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248520666666668, "min": 0.10248520666666668, "max": 0.19828420000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372781000000002, "min": 1.4776313000000003, "max": 2.5730554000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002582721460000001, "min": 0.0002582721460000001, "max": 0.00982859158, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038740821900000015, "min": 0.0038740821900000015, "max": 0.1170352877, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.018007034435868263, "min": 0.017073657363653183, "max": 0.5002771615982056, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2701055109500885, "min": 0.23903121054172516, "max": 4.0022172927856445, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 261.50467289719626, "min": 261.50467289719626, "max": 988.1818181818181, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27981.0, "min": 16383.0, "max": 32610.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7206796097258727, "min": -0.9262875507120043, "max": 1.7206796097258727, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.83339785039425, "min": -30.553001701831818, "max": 185.83339785039425, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7206796097258727, "min": -0.9262875507120043, "max": 1.7206796097258727, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.83339785039425, "min": -30.553001701831818, "max": 185.83339785039425, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04842039830368271, "min": 0.047870229907234066, "max": 9.883193173829246, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.229403016797733, "min": 4.823581758420914, "max": 168.0142839550972, "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": "1742216293", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742219751" }, "total": 3457.266633143, "count": 1, "self": 0.6867554609998479, "children": { "run_training.setup": { "total": 0.026505979000148727, "count": 1, "self": 0.026505979000148727 }, "TrainerController.start_learning": { "total": 3456.5533717030003, "count": 1, "self": 2.447889935020612, "children": { "TrainerController._reset_env": { "total": 3.2666567460000806, "count": 1, "self": 3.2666567460000806 }, "TrainerController.advance": { "total": 3450.7502958689793, "count": 64308, "self": 2.6709190359933928, "children": { "env_step": { "total": 2350.6691946569995, "count": 64308, "self": 2179.263412376985, "children": { "SubprocessEnvManager._take_step": { "total": 170.03456986299625, "count": 64308, "self": 7.398402365994343, "children": { "TorchPolicy.evaluate": { "total": 162.6361674970019, "count": 62563, "self": 162.6361674970019 } } }, "workers": { "total": 1.3712124170181141, "count": 64308, "self": 0.0, "children": { "worker_root": { "total": 3448.7785979520004, "count": 64308, "is_parallel": true, "self": 1447.4587816470216, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029173049999826617, "count": 1, "is_parallel": true, "self": 0.0008516869993400178, "children": { "_process_rank_one_or_two_observation": { "total": 0.002065618000642644, "count": 8, "is_parallel": true, "self": 0.002065618000642644 } } }, "UnityEnvironment.step": { "total": 0.06144978800011813, "count": 1, "is_parallel": true, "self": 0.0006518930001675471, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005609879999610712, "count": 1, "is_parallel": true, "self": 0.0005609879999610712 }, "communicator.exchange": { "total": 0.05836535299999923, "count": 1, "is_parallel": true, "self": 0.05836535299999923 }, "steps_from_proto": { "total": 0.001871553999990283, "count": 1, "is_parallel": true, "self": 0.0004063840001435892, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014651699998466938, "count": 8, "is_parallel": true, "self": 0.0014651699998466938 } } } } } } }, "UnityEnvironment.step": { "total": 2001.3198163049788, "count": 64307, "is_parallel": true, "self": 45.77585770600808, "children": { "UnityEnvironment._generate_step_input": { "total": 32.18439684201644, "count": 64307, "is_parallel": true, "self": 32.18439684201644 }, "communicator.exchange": { "total": 1794.26683990497, "count": 64307, "is_parallel": true, "self": 1794.26683990497 }, "steps_from_proto": { "total": 129.09272185198415, "count": 64307, "is_parallel": true, "self": 28.46875854283485, "children": { "_process_rank_one_or_two_observation": { "total": 100.6239633091493, "count": 514456, "is_parallel": true, "self": 100.6239633091493 } } } } } } } } } } }, "trainer_advance": { "total": 1097.4101821759866, "count": 64308, "self": 4.698705832932319, "children": { "process_trajectory": { "total": 165.72016942605683, "count": 64308, "self": 165.3212438440571, "children": { "RLTrainer._checkpoint": { "total": 0.3989255819997197, "count": 2, "self": 0.3989255819997197 } } }, "_update_policy": { "total": 926.9913069169975, "count": 455, "self": 362.7339156069793, "children": { "TorchPPOOptimizer.update": { "total": 564.2573913100182, "count": 22794, "self": 564.2573913100182 } } } } } } }, "trainer_threads": { "total": 1.3290000424603932e-06, "count": 1, "self": 1.3290000424603932e-06 }, "TrainerController._save_models": { "total": 0.08852782400026626, "count": 1, "self": 0.0032911970001805457, "children": { "RLTrainer._checkpoint": { "total": 0.08523662700008572, "count": 1, "self": 0.08523662700008572 } } } } } } }