{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1367262750864029, "min": 0.13161499798297882, "max": 1.411933183670044, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4108.35107421875, "min": 3918.96826171875, "max": 42832.40625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999979.0, "min": 29897.0, "max": 2999979.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999979.0, "min": 29897.0, "max": 2999979.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8606265187263489, "min": -0.09695502370595932, "max": 0.8710700273513794, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 264.21234130859375, "min": -23.463115692138672, "max": 270.90277099609375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013928480446338654, "min": -0.02460552752017975, "max": 0.4427253007888794, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.27604341506958, "min": -6.938758850097656, "max": 104.92589569091797, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06864624107501917, "min": 0.06416345205313215, "max": 0.07676196047603819, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9610473750502683, "min": 0.5743048212909001, "max": 1.0855401313359228, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014346159985186258, "min": 0.0007752237074949799, "max": 0.016275019457680173, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2008462397926076, "min": 0.010077908197434739, "max": 0.2419713211323445, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4725209377642837e-06, "min": 1.4725209377642837e-06, "max": 0.0002984038380320541, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.061529312869997e-05, "min": 2.061529312869997e-05, "max": 0.0040110078629974, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049080714285714, "min": 0.10049080714285714, "max": 0.19946794583333338, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068713, "min": 1.4068713, "max": 2.7825742333333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9031633571428514e-05, "min": 5.9031633571428514e-05, "max": 0.009946847788750001, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008264428699999992, "min": 0.0008264428699999992, "max": 0.13370655973999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007495376281440258, "min": 0.007033132016658783, "max": 0.5287268757820129, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10493526607751846, "min": 0.09846384823322296, "max": 4.2298150062561035, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 211.20422535211267, "min": 207.3956834532374, "max": 996.6774193548387, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29991.0, "min": 16824.0, "max": 32401.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7747042107225304, "min": -0.9350750520825386, "max": 1.792544820288132, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 252.00799792259932, "min": -29.922401666641235, "max": 259.91899894177914, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7747042107225304, "min": -0.9350750520825386, "max": 1.792544820288132, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 252.00799792259932, "min": -29.922401666641235, "max": 259.91899894177914, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016419117607960877, "min": 0.016419117607960877, "max": 11.133939890300526, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3315147003304446, "min": 2.2355952576181153, "max": 189.27697813510895, "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": "1714416285", "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": "1714423667" }, "total": 7381.973433280001, "count": 1, "self": 0.4787313710012313, "children": { "run_training.setup": { "total": 0.06931593199988129, "count": 1, "self": 0.06931593199988129 }, "TrainerController.start_learning": { "total": 7381.425385977, "count": 1, "self": 4.4047731098262375, "children": { "TrainerController._reset_env": { "total": 2.7422541129999445, "count": 1, "self": 2.7422541129999445 }, "TrainerController.advance": { "total": 7374.192853957174, "count": 195316, "self": 4.278787675103558, "children": { "env_step": { "total": 5465.650000857993, "count": 195316, "self": 5069.03043877189, "children": { "SubprocessEnvManager._take_step": { "total": 393.9534181019967, "count": 195316, "self": 13.7793352652684, "children": { "TorchPolicy.evaluate": { "total": 380.1740828367283, "count": 187566, "self": 380.1740828367283 } } }, "workers": { "total": 2.6661439841068386, "count": 195316, "self": 0.0, "children": { "worker_root": { "total": 7365.411421618755, "count": 195316, "is_parallel": true, "self": 2670.8689167800185, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002571306999925582, "count": 1, "is_parallel": true, "self": 0.0007208100000752893, "children": { "_process_rank_one_or_two_observation": { "total": 0.001850496999850293, "count": 8, "is_parallel": true, "self": 0.001850496999850293 } } }, "UnityEnvironment.step": { "total": 0.04727355200020611, "count": 1, "is_parallel": true, "self": 0.0006255789999158878, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004440729999259929, "count": 1, "is_parallel": true, "self": 0.0004440729999259929 }, "communicator.exchange": { "total": 0.04439002100025391, "count": 1, "is_parallel": true, "self": 0.04439002100025391 }, "steps_from_proto": { "total": 0.0018138790001103189, "count": 1, "is_parallel": true, "self": 0.0003599520005082013, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014539269996021176, "count": 8, "is_parallel": true, "self": 0.0014539269996021176 } } } } } } }, "UnityEnvironment.step": { "total": 4694.542504838737, "count": 195315, "is_parallel": true, "self": 106.17438596514967, "children": { "UnityEnvironment._generate_step_input": { "total": 72.3849658736799, "count": 195315, "is_parallel": true, "self": 72.3849658736799 }, "communicator.exchange": { "total": 4214.67827062394, "count": 195315, "is_parallel": true, "self": 4214.67827062394 }, "steps_from_proto": { "total": 301.3048823759673, "count": 195315, "is_parallel": true, "self": 61.10832164435669, "children": { "_process_rank_one_or_two_observation": { "total": 240.1965607316106, "count": 1562520, "is_parallel": true, "self": 240.1965607316106 } } } } } } } } } } }, "trainer_advance": { "total": 1904.2640654240768, "count": 195316, "self": 8.646408555150629, "children": { "process_trajectory": { "total": 394.7592317699191, "count": 195316, "self": 394.2082910939207, "children": { "RLTrainer._checkpoint": { "total": 0.5509406759983904, "count": 6, "self": 0.5509406759983904 } } }, "_update_policy": { "total": 1500.858425099007, "count": 1404, "self": 877.1083073107543, "children": { "TorchPPOOptimizer.update": { "total": 623.7501177882527, "count": 68346, "self": 623.7501177882527 } } } } } } }, "trainer_threads": { "total": 1.115000486606732e-06, "count": 1, "self": 1.115000486606732e-06 }, "TrainerController._save_models": { "total": 0.0855036819993984, "count": 1, "self": 0.0016083850005088607, "children": { "RLTrainer._checkpoint": { "total": 0.08389529699888953, "count": 1, "self": 0.08389529699888953 } } } } } } }