{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4986371099948883, "min": 0.4962621331214905, "max": 1.4803311824798584, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15094.7421875, "min": 14711.291015625, "max": 44907.328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989953.0, "min": 29994.0, "max": 989953.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989953.0, "min": 29994.0, "max": 989953.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45258212089538574, "min": -0.09443531185388565, "max": 0.5517773628234863, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 121.29200744628906, "min": -22.664474487304688, "max": 151.08238220214844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01688561961054802, "min": -0.014703236520290375, "max": 0.30960240960121155, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.525346279144287, "min": -3.734622001647949, "max": 74.61418151855469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06579662856594141, "min": 0.06377845886750381, "max": 0.07298209077152959, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9869494284891213, "min": 0.5012847703597882, "max": 1.0377062588425665, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012565838324371727, "min": 9.199154153914886e-05, "max": 0.014226614192011764, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1884875748655759, "min": 0.0011958900400089352, "max": 0.1991725986881647, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.504037498686665e-06, "min": 7.504037498686665e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011256056248029997, "min": 0.00011256056248029997, "max": 0.0036340153886616003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250131333333333, "min": 0.10250131333333333, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375197, "min": 1.3886848, "max": 2.6113384, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000259881202, "min": 0.000259881202, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038982180300000005, "min": 0.0038982180300000005, "max": 0.12115270616000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009382353164255619, "min": 0.009382353164255619, "max": 0.47432413697242737, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14073529839515686, "min": 0.13849836587905884, "max": 3.3202688694000244, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 431.6666666666667, "min": 354.4457831325301, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28490.0, "min": 16793.0, "max": 33312.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4470757304719, "min": -0.9998533852398396, "max": 1.5426214076578617, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 95.5069982111454, "min": -31.995201662182808, "max": 129.58019824326038, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4470757304719, "min": -0.9998533852398396, "max": 1.5426214076578617, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 95.5069982111454, "min": -31.995201662182808, "max": 129.58019824326038, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04185799672180138, "min": 0.03936679322978307, "max": 8.745527979205637, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.762627783638891, "min": 2.762627783638891, "max": 148.67397564649582, "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": "1698181469", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698183633" }, "total": 2163.837711037, "count": 1, "self": 0.47559117400032846, "children": { "run_training.setup": { "total": 0.04523894800013295, "count": 1, "self": 0.04523894800013295 }, "TrainerController.start_learning": { "total": 2163.3168809149997, "count": 1, "self": 1.3401762560547468, "children": { "TrainerController._reset_env": { "total": 3.5537536130000262, "count": 1, "self": 3.5537536130000262 }, "TrainerController.advance": { "total": 2158.3508822979443, "count": 63552, "self": 1.4157601830406747, "children": { "env_step": { "total": 1526.5134747409998, "count": 63552, "self": 1396.4239817381826, "children": { "SubprocessEnvManager._take_step": { "total": 129.2821725410099, "count": 63552, "self": 4.627384684040862, "children": { "TorchPolicy.evaluate": { "total": 124.65478785696905, "count": 62560, "self": 124.65478785696905 } } }, "workers": { "total": 0.8073204618071941, "count": 63552, "self": 0.0, "children": { "worker_root": { "total": 2158.766530230962, "count": 63552, "is_parallel": true, "self": 875.8935204110066, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00174897199985935, "count": 1, "is_parallel": true, "self": 0.0005821549998472619, "children": { "_process_rank_one_or_two_observation": { "total": 0.001166817000012088, "count": 8, "is_parallel": true, "self": 0.001166817000012088 } } }, "UnityEnvironment.step": { "total": 0.047315836000052514, "count": 1, "is_parallel": true, "self": 0.0005642279998028243, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004619370001819334, "count": 1, "is_parallel": true, "self": 0.0004619370001819334 }, "communicator.exchange": { "total": 0.044167027000185044, "count": 1, "is_parallel": true, "self": 0.044167027000185044 }, "steps_from_proto": { "total": 0.002122643999882712, "count": 1, "is_parallel": true, "self": 0.0006738330007465265, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014488109991361853, "count": 8, "is_parallel": true, "self": 0.0014488109991361853 } } } } } } }, "UnityEnvironment.step": { "total": 1282.8730098199553, "count": 63551, "is_parallel": true, "self": 34.8070860459361, "children": { "UnityEnvironment._generate_step_input": { "total": 23.748803471014526, "count": 63551, "is_parallel": true, "self": 23.748803471014526 }, "communicator.exchange": { "total": 1127.2700299869784, "count": 63551, "is_parallel": true, "self": 1127.2700299869784 }, "steps_from_proto": { "total": 97.04709031602624, "count": 63551, "is_parallel": true, "self": 19.208051326192617, "children": { "_process_rank_one_or_two_observation": { "total": 77.83903898983363, "count": 508408, "is_parallel": true, "self": 77.83903898983363 } } } } } } } } } } }, "trainer_advance": { "total": 630.4216473739039, "count": 63552, "self": 2.491393568897365, "children": { "process_trajectory": { "total": 121.31617968501405, "count": 63552, "self": 121.15885107901386, "children": { "RLTrainer._checkpoint": { "total": 0.15732860600019194, "count": 2, "self": 0.15732860600019194 } } }, "_update_policy": { "total": 506.61407411999244, "count": 449, "self": 303.3752762980557, "children": { "TorchPPOOptimizer.update": { "total": 203.2387978219367, "count": 22776, "self": 203.2387978219367 } } } } } } }, "trainer_threads": { "total": 1.0120002116309479e-06, "count": 1, "self": 1.0120002116309479e-06 }, "TrainerController._save_models": { "total": 0.0720677360004629, "count": 1, "self": 0.0013900849999117781, "children": { "RLTrainer._checkpoint": { "total": 0.07067765100055112, "count": 1, "self": 0.07067765100055112 } } } } } } }