{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43044039607048035, "min": 0.4232605993747711, "max": 1.2874609231948853, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12892.55078125, "min": 12596.2353515625, "max": 39056.4140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989902.0, "min": 29963.0, "max": 989902.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989902.0, "min": 29963.0, "max": 989902.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5394355058670044, "min": -0.11496417224407196, "max": 0.5394355058670044, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 148.34475708007812, "min": -27.82132911682129, "max": 148.34475708007812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.20778167247772217, "min": -0.2441752552986145, "max": 0.41229933500289917, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 57.13996124267578, "min": -63.973915100097656, "max": 98.12724304199219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0669255613860774, "min": 0.06242154989463632, "max": 0.07571350690067083, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9369578594050837, "min": 0.6792921543429088, "max": 1.0661665600685712, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01602240451041051, "min": 0.0002817554371297112, "max": 0.024683490512307754, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22431366314574713, "min": 0.0036628206826862454, "max": 0.34556886717230856, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.510190353778569e-06, "min": 7.510190353778569e-06, "max": 0.0002948771017076334, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010514266495289996, "min": 0.00010514266495289996, "max": 0.0036334585888471997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025033642857143, "min": 0.1025033642857143, "max": 0.19829236666666666, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350471000000002, "min": 1.4350471000000002, "max": 2.6111527999999993, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026008609214285707, "min": 0.00026008609214285707, "max": 0.00982940743, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003641205289999999, "min": 0.003641205289999999, "max": 0.12113416471999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0133809894323349, "min": 0.0133809894323349, "max": 0.5212202668190002, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1873338520526886, "min": 0.1873338520526886, "max": 4.690982341766357, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 345.7325581395349, "min": 345.7325581395349, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29733.0, "min": 17401.0, "max": 32655.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5839458611958168, "min": -0.9998774711162813, "max": 1.5839458611958168, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.63539820164442, "min": -30.99620160460472, "max": 136.2625983208418, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5839458611958168, "min": -0.9998774711162813, "max": 1.5839458611958168, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.63539820164442, "min": -30.99620160460472, "max": 136.2625983208418, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047659866179695684, "min": 0.047659866179695684, "max": 9.543598460654417, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.051088625274133, "min": 4.048533490800764, "max": 171.78477229177952, "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": "1702581933", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702584130" }, "total": 2196.862197849, "count": 1, "self": 0.4936809139999241, "children": { "run_training.setup": { "total": 0.05087635700010651, "count": 1, "self": 0.05087635700010651 }, "TrainerController.start_learning": { "total": 2196.317640578, "count": 1, "self": 1.356258463949871, "children": { "TrainerController._reset_env": { "total": 3.6979038590000073, "count": 1, "self": 3.6979038590000073 }, "TrainerController.advance": { "total": 2191.18310169105, "count": 63806, "self": 1.4198867619961675, "children": { "env_step": { "total": 1558.8987405940118, "count": 63806, "self": 1432.0676027180305, "children": { "SubprocessEnvManager._take_step": { "total": 125.99727272798827, "count": 63806, "self": 4.73098126990385, "children": { "TorchPolicy.evaluate": { "total": 121.26629145808442, "count": 62570, "self": 121.26629145808442 } } }, "workers": { "total": 0.8338651479930377, "count": 63806, "self": 0.0, "children": { "worker_root": { "total": 2191.304855199, "count": 63806, "is_parallel": true, "self": 878.1099026559987, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006951646000061373, "count": 1, "is_parallel": true, "self": 0.005762026999946102, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011896190001152718, "count": 8, "is_parallel": true, "self": 0.0011896190001152718 } } }, "UnityEnvironment.step": { "total": 0.0733953180001663, "count": 1, "is_parallel": true, "self": 0.0006574770002316654, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048028699984570267, "count": 1, "is_parallel": true, "self": 0.00048028699984570267 }, "communicator.exchange": { "total": 0.07066155699999399, "count": 1, "is_parallel": true, "self": 0.07066155699999399 }, "steps_from_proto": { "total": 0.0015959970000949397, "count": 1, "is_parallel": true, "self": 0.00033455200036769384, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012614449997272459, "count": 8, "is_parallel": true, "self": 0.0012614449997272459 } } } } } } }, "UnityEnvironment.step": { "total": 1313.1949525430014, "count": 63805, "is_parallel": true, "self": 35.54912352103702, "children": { "UnityEnvironment._generate_step_input": { "total": 24.15549091101593, "count": 63805, "is_parallel": true, "self": 24.15549091101593 }, "communicator.exchange": { "total": 1153.9066822880127, "count": 63805, "is_parallel": true, "self": 1153.9066822880127 }, "steps_from_proto": { "total": 99.58365582293573, "count": 63805, "is_parallel": true, "self": 19.59839368403709, "children": { "_process_rank_one_or_two_observation": { "total": 79.98526213889863, "count": 510440, "is_parallel": true, "self": 79.98526213889863 } } } } } } } } } } }, "trainer_advance": { "total": 630.8644743350419, "count": 63806, "self": 2.753469361000043, "children": { "process_trajectory": { "total": 127.95773141104382, "count": 63806, "self": 127.77507564104371, "children": { "RLTrainer._checkpoint": { "total": 0.18265577000011035, "count": 2, "self": 0.18265577000011035 } } }, "_update_policy": { "total": 500.15327356299804, "count": 458, "self": 296.15334318598934, "children": { "TorchPPOOptimizer.update": { "total": 203.9999303770087, "count": 22782, "self": 203.9999303770087 } } } } } } }, "trainer_threads": { "total": 1.297999915550463e-06, "count": 1, "self": 1.297999915550463e-06 }, "TrainerController._save_models": { "total": 0.08037526600037381, "count": 1, "self": 0.0013400689999798487, "children": { "RLTrainer._checkpoint": { "total": 0.07903519700039396, "count": 1, "self": 0.07903519700039396 } } } } } } }