{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1700042486190796, "min": 0.16756978631019592, "max": 1.433391809463501, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5130.04833984375, "min": 4992.2392578125, "max": 43483.375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999977.0, "min": 29952.0, "max": 2999977.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999977.0, "min": 29952.0, "max": 2999977.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8148308992385864, "min": -0.10425473749637604, "max": 0.8639565706253052, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 238.74545288085938, "min": -25.021137237548828, "max": 261.7788391113281, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010775096714496613, "min": -0.025844106450676918, "max": 0.37296047806739807, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.1571033000946045, "min": -6.977908611297607, "max": 88.39163208007812, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06551541737908516, "min": 0.06385610242436526, "max": 0.07586080297457447, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9172158433071922, "min": 0.4893866748828039, "max": 1.13370390004346, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016971619242561933, "min": 0.0004244538121253843, "max": 0.016971619242561933, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23760266939586708, "min": 0.004244538121253843, "max": 0.243499810564875, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5286066333547625e-06, "min": 1.5286066333547625e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1400492866966676e-05, "min": 2.1400492866966676e-05, "max": 0.0038478239173920996, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050950238095238, "min": 0.10050950238095238, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071330333333334, "min": 1.3897045333333333, "max": 2.7826079, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.08992878571429e-05, "min": 6.08992878571429e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008525900300000006, "min": 0.0008525900300000006, "max": 0.12828252921, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006674718577414751, "min": 0.006674718577414751, "max": 0.4300249516963959, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09344606101512909, "min": 0.09344606101512909, "max": 3.0101747512817383, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 232.952, "min": 210.5985401459854, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29119.0, "min": 15984.0, "max": 33124.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7347322407989734, "min": -1.0000000521540642, "max": 1.788691166897907, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 215.10679785907269, "min": -32.000001668930054, "max": 253.90399800240993, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7347322407989734, "min": -1.0000000521540642, "max": 1.788691166897907, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 215.10679785907269, "min": -32.000001668930054, "max": 253.90399800240993, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016401921517524076, "min": 0.014885524053934732, "max": 8.116330409422517, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0338382681729854, "min": 2.023874742575572, "max": 129.86128655076027, "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": "1730205544", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/zfh_unix/anaconda3/envs/drl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1730211857" }, "total": 5095.723477269003, "count": 1, "self": 0.2705190149972623, "children": { "run_training.setup": { "total": 0.010829730003024451, "count": 1, "self": 0.010829730003024451 }, "TrainerController.start_learning": { "total": 5095.442128524002, "count": 1, "self": 3.093955257740163, "children": { "TrainerController._reset_env": { "total": 3.113347802001954, "count": 1, "self": 3.113347802001954 }, "TrainerController.advance": { "total": 5089.159548576263, "count": 195396, "self": 3.047439839621802, "children": { "env_step": { "total": 3425.7349329134377, "count": 195396, "self": 2889.09674456804, "children": { "SubprocessEnvManager._take_step": { "total": 534.5402734787494, "count": 195396, "self": 9.363236880886689, "children": { "TorchPolicy.evaluate": { "total": 525.1770365978628, "count": 187559, "self": 525.1770365978628 } } }, "workers": { "total": 2.0979148666483525, "count": 195396, "self": 0.0, "children": { "worker_root": { "total": 5087.645380384434, "count": 195396, "is_parallel": true, "self": 2401.3574907899747, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001159678999101743, "count": 1, "is_parallel": true, "self": 0.00038356699951691553, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007761119995848276, "count": 8, "is_parallel": true, "self": 0.0007761119995848276 } } }, "UnityEnvironment.step": { "total": 0.02414702899841359, "count": 1, "is_parallel": true, "self": 0.00018160499894293025, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015605299995513633, "count": 1, "is_parallel": true, "self": 0.00015605299995513633 }, "communicator.exchange": { "total": 0.02329539600032149, "count": 1, "is_parallel": true, "self": 0.02329539600032149 }, "steps_from_proto": { "total": 0.0005139749991940334, "count": 1, "is_parallel": true, "self": 0.00012966100257472135, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003843139966193121, "count": 8, "is_parallel": true, "self": 0.0003843139966193121 } } } } } } }, "UnityEnvironment.step": { "total": 2686.2878895944596, "count": 195395, "is_parallel": true, "self": 36.89949924704706, "children": { "UnityEnvironment._generate_step_input": { "total": 24.117771501256357, "count": 195395, "is_parallel": true, "self": 24.117771501256357 }, "communicator.exchange": { "total": 2528.2641570351298, "count": 195395, "is_parallel": true, "self": 2528.2641570351298 }, "steps_from_proto": { "total": 97.00646181102638, "count": 195395, "is_parallel": true, "self": 22.479456310240494, "children": { "_process_rank_one_or_two_observation": { "total": 74.52700550078589, "count": 1563160, "is_parallel": true, "self": 74.52700550078589 } } } } } } } } } } }, "trainer_advance": { "total": 1660.3771758232033, "count": 195396, "self": 5.747511579735146, "children": { "process_trajectory": { "total": 271.04134825235815, "count": 195396, "self": 270.61661393936083, "children": { "RLTrainer._checkpoint": { "total": 0.424734312997316, "count": 6, "self": 0.424734312997316 } } }, "_update_policy": { "total": 1383.58831599111, "count": 1383, "self": 553.0646376604782, "children": { "TorchPPOOptimizer.update": { "total": 830.5236783306318, "count": 68487, "self": 830.5236783306318 } } } } } } }, "trainer_threads": { "total": 6.659975042566657e-07, "count": 1, "self": 6.659975042566657e-07 }, "TrainerController._save_models": { "total": 0.07527622199995676, "count": 1, "self": 0.0008994329982670024, "children": { "RLTrainer._checkpoint": { "total": 0.07437678900168976, "count": 1, "self": 0.07437678900168976 } } } } } } }