{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32846593856811523, "min": 0.32846593856811523, "max": 1.455418586730957, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9875.0, "min": 9875.0, "max": 44151.578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.570151686668396, "min": -0.09297454357147217, "max": 0.570151686668396, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.92308044433594, "min": -22.406864166259766, "max": 161.92308044433594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.011242495849728584, "min": -0.02884085662662983, "max": 0.2717488706111908, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.192868709564209, "min": -7.094850540161133, "max": 65.4914779663086, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07088984576763498, "min": 0.06528661026955576, "max": 0.07451107542562697, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9924578407468896, "min": 0.5155871145282711, "max": 1.051984154603298, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015956498018654418, "min": 0.00022249645558307656, "max": 0.01681934588616329, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22339097226116184, "min": 0.002892453922579995, "max": 0.23547084240628607, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.349304693121432e-06, "min": 7.349304693121432e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010289026570370005, "min": 0.00010289026570370005, "max": 0.0036327511890829997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244973571428573, "min": 0.10244973571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342963000000002, "min": 1.3886848, "max": 2.6109169999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025472859785714304, "min": 0.00025472859785714304, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035662003700000023, "min": 0.0035662003700000023, "max": 0.12111060829999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012695064768195152, "min": 0.012695064768195152, "max": 0.3957328796386719, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17773090302944183, "min": 0.17773090302944183, "max": 2.770130157470703, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 310.49484536082474, "min": 310.49484536082474, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30118.0, "min": 15984.0, "max": 34842.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6895051365046156, "min": -1.0000000521540642, "max": 1.6895051365046156, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.88199824094772, "min": -29.997201591730118, "max": 163.88199824094772, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6895051365046156, "min": -1.0000000521540642, "max": 1.6895051365046156, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.88199824094772, "min": -29.997201591730118, "max": 163.88199824094772, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04097032838196646, "min": 0.04097032838196646, "max": 7.656364715658128, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9741218530507467, "min": 3.966332409516326, "max": 122.50183545053005, "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": "1696216280", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1696218596" }, "total": 2316.4659534889997, "count": 1, "self": 0.8548761499996544, "children": { "run_training.setup": { "total": 0.06506582799988792, "count": 1, "self": 0.06506582799988792 }, "TrainerController.start_learning": { "total": 2315.546011511, "count": 1, "self": 1.3845496130511492, "children": { "TrainerController._reset_env": { "total": 5.078607113000089, "count": 1, "self": 5.078607113000089 }, "TrainerController.advance": { "total": 2308.9258635529486, "count": 63823, "self": 1.3580597349646268, "children": { "env_step": { "total": 1638.0729142429632, "count": 63823, "self": 1528.737767837917, "children": { "SubprocessEnvManager._take_step": { "total": 108.51000391605407, "count": 63823, "self": 4.665571416114062, "children": { "TorchPolicy.evaluate": { "total": 103.84443249994001, "count": 62548, "self": 103.84443249994001 } } }, "workers": { "total": 0.8251424889920145, "count": 63823, "self": 0.0, "children": { "worker_root": { "total": 2309.9691839720526, "count": 63823, "is_parallel": true, "self": 895.4351654260875, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026563599999462895, "count": 1, "is_parallel": true, "self": 0.0007403039999189787, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019160560000273108, "count": 8, "is_parallel": true, "self": 0.0019160560000273108 } } }, "UnityEnvironment.step": { "total": 0.047437200000103985, "count": 1, "is_parallel": true, "self": 0.0005837809999320598, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005060910000338481, "count": 1, "is_parallel": true, "self": 0.0005060910000338481 }, "communicator.exchange": { "total": 0.04366749800010439, "count": 1, "is_parallel": true, "self": 0.04366749800010439 }, "steps_from_proto": { "total": 0.0026798300000336894, "count": 1, "is_parallel": true, "self": 0.0003492420000839047, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023305879999497847, "count": 8, "is_parallel": true, "self": 0.0023305879999497847 } } } } } } }, "UnityEnvironment.step": { "total": 1414.5340185459652, "count": 63822, "is_parallel": true, "self": 33.78076866198103, "children": { "UnityEnvironment._generate_step_input": { "total": 23.049014497969665, "count": 63822, "is_parallel": true, "self": 23.049014497969665 }, "communicator.exchange": { "total": 1253.9083839499501, "count": 63822, "is_parallel": true, "self": 1253.9083839499501 }, "steps_from_proto": { "total": 103.79585143606437, "count": 63822, "is_parallel": true, "self": 20.435371406866352, "children": { "_process_rank_one_or_two_observation": { "total": 83.36048002919802, "count": 510576, "is_parallel": true, "self": 83.36048002919802 } } } } } } } } } } }, "trainer_advance": { "total": 669.4948895750208, "count": 63823, "self": 2.5577473480600474, "children": { "process_trajectory": { "total": 109.60221011995463, "count": 63823, "self": 109.34100844595423, "children": { "RLTrainer._checkpoint": { "total": 0.2612016740004037, "count": 2, "self": 0.2612016740004037 } } }, "_update_policy": { "total": 557.3349321070061, "count": 453, "self": 366.09167929403475, "children": { "TorchPPOOptimizer.update": { "total": 191.24325281297138, "count": 22803, "self": 191.24325281297138 } } } } } } }, "trainer_threads": { "total": 1.635999979043845e-06, "count": 1, "self": 1.635999979043845e-06 }, "TrainerController._save_models": { "total": 0.1569895960001304, "count": 1, "self": 0.0018932640000457468, "children": { "RLTrainer._checkpoint": { "total": 0.15509633200008466, "count": 1, "self": 0.15509633200008466 } } } } } } }