{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.323770672082901, "min": 0.323770672082901, "max": 1.4582098722457886, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9759.7431640625, "min": 9759.7431640625, "max": 44236.25390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989895.0, "min": 29915.0, "max": 989895.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989895.0, "min": 29915.0, "max": 989895.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49555015563964844, "min": -0.13686437904834747, "max": 0.6415801048278809, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 130.8252410888672, "min": -32.57372283935547, "max": 181.56716918945312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.011162635870277882, "min": -0.011162635870277882, "max": 0.26784929633140564, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.9469358921051025, "min": -2.9469358921051025, "max": 64.55168151855469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06477152436143821, "min": 0.06477152436143821, "max": 0.07273734795738009, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9715728654215732, "min": 0.5766963413077729, "max": 1.0643582190021728, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01423398255525778, "min": 0.0005055835248906022, "max": 0.015414487217833889, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2135097383288667, "min": 0.006067002298687226, "max": 0.21986013003333937, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.521337492920005e-06, "min": 7.521337492920005e-06, "max": 0.0002948502392165875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011282006239380008, "min": 0.00011282006239380008, "max": 0.003508413530528899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250708000000001, "min": 0.10250708000000001, "max": 0.1982834125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376062000000001, "min": 1.4776548, "max": 2.5694710999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026045729200000015, "min": 0.00026045729200000015, "max": 0.00982851290875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003906859380000002, "min": 0.003906859380000002, "max": 0.11697016289000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01812346652150154, "min": 0.01812346652150154, "max": 0.4680212736129761, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2718519866466522, "min": 0.2669598162174225, "max": 3.7441701889038086, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 389.17283950617286, "min": 336.96774193548384, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31523.0, "min": 16969.0, "max": 32699.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4132493548555138, "min": -0.9999500517733395, "max": 1.571856159172701, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.47319774329662, "min": -31.998401656746864, "max": 144.65899857878685, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4132493548555138, "min": -0.9999500517733395, "max": 1.571856159172701, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.47319774329662, "min": -31.998401656746864, "max": 144.65899857878685, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07258195938962156, "min": 0.06830586166168222, "max": 8.162659615278244, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.879138710559346, "min": 5.396163071272895, "max": 146.9278730750084, "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": "1738450332", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738452704" }, "total": 2371.3287003059995, "count": 1, "self": 0.5264948510002796, "children": { "run_training.setup": { "total": 0.030683930999657605, "count": 1, "self": 0.030683930999657605 }, "TrainerController.start_learning": { "total": 2370.7715215239996, "count": 1, "self": 1.481143858023188, "children": { "TrainerController._reset_env": { "total": 2.244592248999652, "count": 1, "self": 2.244592248999652 }, "TrainerController.advance": { "total": 2366.951290260977, "count": 63824, "self": 1.5431029529468105, "children": { "env_step": { "total": 1648.2647548129257, "count": 63824, "self": 1479.8927231679654, "children": { "SubprocessEnvManager._take_step": { "total": 167.49660390002782, "count": 63824, "self": 5.003764071965179, "children": { "TorchPolicy.evaluate": { "total": 162.49283982806264, "count": 62557, "self": 162.49283982806264 } } }, "workers": { "total": 0.8754277449324945, "count": 63824, "self": 0.0, "children": { "worker_root": { "total": 2365.041919946991, "count": 63824, "is_parallel": true, "self": 1008.47313007404, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002063453999653575, "count": 1, "is_parallel": true, "self": 0.0006883389992253797, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013751150004281953, "count": 8, "is_parallel": true, "self": 0.0013751150004281953 } } }, "UnityEnvironment.step": { "total": 0.052112123999904725, "count": 1, "is_parallel": true, "self": 0.0005389189996094501, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007047650001368311, "count": 1, "is_parallel": true, "self": 0.0007047650001368311 }, "communicator.exchange": { "total": 0.04913821300033305, "count": 1, "is_parallel": true, "self": 0.04913821300033305 }, "steps_from_proto": { "total": 0.0017302269998253905, "count": 1, "is_parallel": true, "self": 0.00035096299961878685, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013792640002066037, "count": 8, "is_parallel": true, "self": 0.0013792640002066037 } } } } } } }, "UnityEnvironment.step": { "total": 1356.5687898729511, "count": 63823, "is_parallel": true, "self": 33.35161664508223, "children": { "UnityEnvironment._generate_step_input": { "total": 24.426625246936965, "count": 63823, "is_parallel": true, "self": 24.426625246936965 }, "communicator.exchange": { "total": 1195.464377916011, "count": 63823, "is_parallel": true, "self": 1195.464377916011 }, "steps_from_proto": { "total": 103.32617006492092, "count": 63823, "is_parallel": true, "self": 20.968925834036327, "children": { "_process_rank_one_or_two_observation": { "total": 82.35724423088459, "count": 510584, "is_parallel": true, "self": 82.35724423088459 } } } } } } } } } } }, "trainer_advance": { "total": 717.1434324951047, "count": 63824, "self": 2.8409659511489735, "children": { "process_trajectory": { "total": 139.40505516995745, "count": 63824, "self": 139.19528470095793, "children": { "RLTrainer._checkpoint": { "total": 0.20977046899952256, "count": 2, "self": 0.20977046899952256 } } }, "_update_policy": { "total": 574.8974113739982, "count": 456, "self": 316.4368406340377, "children": { "TorchPPOOptimizer.update": { "total": 258.46057073996053, "count": 22773, "self": 258.46057073996053 } } } } } } }, "trainer_threads": { "total": 1.1829997674794868e-06, "count": 1, "self": 1.1829997674794868e-06 }, "TrainerController._save_models": { "total": 0.09449397299977136, "count": 1, "self": 0.0014072179992581368, "children": { "RLTrainer._checkpoint": { "total": 0.09308675500051322, "count": 1, "self": 0.09308675500051322 } } } } } } }