{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7388007044792175, "min": 0.7309030294418335, "max": 1.352487564086914, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22104.91796875, "min": 21915.396484375, "max": 41029.0625, "count": 33 }, "Pyramids.Step.mean": { "value": 989946.0, "min": 29952.0, "max": 989946.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989946.0, "min": 29952.0, "max": 989946.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3870429992675781, "min": -0.102423295378685, "max": 0.4368783235549927, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 101.40526580810547, "min": -24.58159065246582, "max": 115.46650695800781, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.6684350371360779, "min": -0.03654031828045845, "max": 0.6684350371360779, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 175.12997436523438, "min": -9.610103607177734, "max": 175.12997436523438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06697335998233896, "min": 0.06463177804142192, "max": 0.07360926340248518, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9376270397527453, "min": 0.509531025694825, "max": 1.0491946983526634, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.05182982837071731, "min": 0.00010431107823909638, "max": 0.05182982837071731, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.7256175971900424, "min": 0.001356044017108253, "max": 0.7256175971900424, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.522661778192853e-06, "min": 7.522661778192853e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010531726489469995, "min": 0.00010531726489469995, "max": 0.0035083277305574994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250752142857145, "min": 0.10250752142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351053000000003, "min": 1.3886848, "max": 2.5694425000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002605013907142856, "min": 0.0002605013907142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003647019469999998, "min": 0.003647019469999998, "max": 0.11696730575000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010956819169223309, "min": 0.010956819169223309, "max": 0.5902058482170105, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15339547395706177, "min": 0.15339547395706177, "max": 4.131441116333008, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 457.7258064516129, "min": 420.18840579710144, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28379.0, "min": 15984.0, "max": 32727.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4777386837428617, "min": -1.0000000521540642, "max": 1.4777386837428617, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 91.61979839205742, "min": -31.994001641869545, "max": 99.00439910590649, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4777386837428617, "min": -1.0000000521540642, "max": 1.4777386837428617, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 91.61979839205742, "min": -31.994001641869545, "max": 99.00439910590649, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05127620012424285, "min": 0.04797805202964599, "max": 12.12938067317009, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.179124407703057, "min": 3.179124407703057, "max": 194.07009077072144, "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": "1690519591", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1690521720" }, "total": 2129.059600501, "count": 1, "self": 0.49079215900019335, "children": { "run_training.setup": { "total": 0.04009146300006705, "count": 1, "self": 0.04009146300006705 }, "TrainerController.start_learning": { "total": 2128.528716879, "count": 1, "self": 1.2905530479906702, "children": { "TrainerController._reset_env": { "total": 5.673141665000003, "count": 1, "self": 5.673141665000003 }, "TrainerController.advance": { "total": 2121.4683262150093, "count": 63499, "self": 1.3397961900059272, "children": { "env_step": { "total": 1465.1186691410085, "count": 63499, "self": 1359.910134592059, "children": { "SubprocessEnvManager._take_step": { "total": 104.40756369499809, "count": 63499, "self": 4.544769550013939, "children": { "TorchPolicy.evaluate": { "total": 99.86279414498415, "count": 62570, "self": 99.86279414498415 } } }, "workers": { "total": 0.8009708539515259, "count": 63499, "self": 0.0, "children": { "worker_root": { "total": 2123.8423002649506, "count": 63499, "is_parallel": true, "self": 873.6422860289599, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005351331000042592, "count": 1, "is_parallel": true, "self": 0.00398783400009961, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013634969999429813, "count": 8, "is_parallel": true, "self": 0.0013634969999429813 } } }, "UnityEnvironment.step": { "total": 0.04939262499999586, "count": 1, "is_parallel": true, "self": 0.0006072620000168172, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004958630000828634, "count": 1, "is_parallel": true, "self": 0.0004958630000828634 }, "communicator.exchange": { "total": 0.046303006999892204, "count": 1, "is_parallel": true, "self": 0.046303006999892204 }, "steps_from_proto": { "total": 0.001986493000003975, "count": 1, "is_parallel": true, "self": 0.00038619400027073425, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016002989997332406, "count": 8, "is_parallel": true, "self": 0.0016002989997332406 } } } } } } }, "UnityEnvironment.step": { "total": 1250.2000142359907, "count": 63498, "is_parallel": true, "self": 34.595276643995476, "children": { "UnityEnvironment._generate_step_input": { "total": 23.07112084896994, "count": 63498, "is_parallel": true, "self": 23.07112084896994 }, "communicator.exchange": { "total": 1091.0033152240176, "count": 63498, "is_parallel": true, "self": 1091.0033152240176 }, "steps_from_proto": { "total": 101.5303015190076, "count": 63498, "is_parallel": true, "self": 20.45111614986888, "children": { "_process_rank_one_or_two_observation": { "total": 81.07918536913871, "count": 507984, "is_parallel": true, "self": 81.07918536913871 } } } } } } } } } } }, "trainer_advance": { "total": 655.0098608839949, "count": 63499, "self": 2.360604709960967, "children": { "process_trajectory": { "total": 107.74699612603786, "count": 63499, "self": 107.48648748603796, "children": { "RLTrainer._checkpoint": { "total": 0.26050863999989815, "count": 2, "self": 0.26050863999989815 } } }, "_update_policy": { "total": 544.902260047996, "count": 448, "self": 356.93628246099, "children": { "TorchPPOOptimizer.update": { "total": 187.96597758700602, "count": 22863, "self": 187.96597758700602 } } } } } } }, "trainer_threads": { "total": 1.02400008472614e-06, "count": 1, "self": 1.02400008472614e-06 }, "TrainerController._save_models": { "total": 0.09669492700004412, "count": 1, "self": 0.0013963810001769161, "children": { "RLTrainer._checkpoint": { "total": 0.0952985459998672, "count": 1, "self": 0.0952985459998672 } } } } } } }