{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3142242431640625, "min": 0.3142242431640625, "max": 1.4658249616622925, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9497.11328125, "min": 9497.11328125, "max": 44467.265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989937.0, "min": 29952.0, "max": 989937.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47683265805244446, "min": -0.2572888433933258, "max": 0.47683265805244446, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.698486328125, "min": -60.977455139160156, "max": 129.698486328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04313739016652107, "min": -0.04313739016652107, "max": 0.43667465448379517, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.733369827270508, "min": -11.733369827270508, "max": 103.49188995361328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07023988753607423, "min": 0.06272303400308002, "max": 0.07331832827954694, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0535983130411135, "min": 0.5132282979568286, "max": 1.0535983130411135, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01433547756148067, "min": 0.00013381286774667012, "max": 0.01433547756148067, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21503216342221004, "min": 0.0017395672807067116, "max": 0.21503216342221004, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.453597515499999e-06, "min": 7.453597515499999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011180396273249999, "min": 0.00011180396273249999, "max": 0.0035078072307309993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248450000000002, "min": 0.10248450000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372675000000002, "min": 1.3886848, "max": 2.5692690000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025820155000000003, "min": 0.00025820155000000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00387302325, "min": 0.00387302325, "max": 0.1169499731, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014570423401892185, "min": 0.014570423401892185, "max": 0.5203476548194885, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21855634450912476, "min": 0.20461633801460266, "max": 3.6424334049224854, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 411.89473684210526, "min": 387.3783783783784, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31304.0, "min": 15984.0, "max": 32541.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4828105088519423, "min": -1.0000000521540642, "max": 1.497505692073277, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.69359867274761, "min": -31.99320162832737, "max": 112.69359867274761, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4828105088519423, "min": -1.0000000521540642, "max": 1.497505692073277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.69359867274761, "min": -31.99320162832737, "max": 112.69359867274761, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.061423001488468514, "min": 0.060450017597365846, "max": 10.782642115838826, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.668148113123607, "min": 4.473301302205073, "max": 172.5222738534212, "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": "1681725493", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "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": "1681727586" }, "total": 2093.129246688, "count": 1, "self": 0.4748499679994893, "children": { "run_training.setup": { "total": 0.11688721300015459, "count": 1, "self": 0.11688721300015459 }, "TrainerController.start_learning": { "total": 2092.5375095070003, "count": 1, "self": 1.4138793889806038, "children": { "TrainerController._reset_env": { "total": 3.793426436000118, "count": 1, "self": 3.793426436000118 }, "TrainerController.advance": { "total": 2087.2353523440206, "count": 63646, "self": 1.434748125886017, "children": { "env_step": { "total": 1479.6305073981202, "count": 63646, "self": 1373.3664187370891, "children": { "SubprocessEnvManager._take_step": { "total": 105.42257611303103, "count": 63646, "self": 4.735638717073471, "children": { "TorchPolicy.evaluate": { "total": 100.68693739595756, "count": 62575, "self": 100.68693739595756 } } }, "workers": { "total": 0.8415125480000825, "count": 63646, "self": 0.0, "children": { "worker_root": { "total": 2087.577791341044, "count": 63646, "is_parallel": true, "self": 822.9442456119955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001705107999896427, "count": 1, "is_parallel": true, "self": 0.0005499479998434254, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011551600000530016, "count": 8, "is_parallel": true, "self": 0.0011551600000530016 } } }, "UnityEnvironment.step": { "total": 0.044999272000040946, "count": 1, "is_parallel": true, "self": 0.0005131240000082471, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030612199998358847, "count": 1, "is_parallel": true, "self": 0.00030612199998358847 }, "communicator.exchange": { "total": 0.042602158000136114, "count": 1, "is_parallel": true, "self": 0.042602158000136114 }, "steps_from_proto": { "total": 0.0015778679999129963, "count": 1, "is_parallel": true, "self": 0.0003718719999596942, "children": { "_process_rank_one_or_two_observation": { "total": 0.001205995999953302, "count": 8, "is_parallel": true, "self": 0.001205995999953302 } } } } } } }, "UnityEnvironment.step": { "total": 1264.6335457290484, "count": 63645, "is_parallel": true, "self": 31.913115142187507, "children": { "UnityEnvironment._generate_step_input": { "total": 22.852449078042355, "count": 63645, "is_parallel": true, "self": 22.852449078042355 }, "communicator.exchange": { "total": 1117.2035838069382, "count": 63645, "is_parallel": true, "self": 1117.2035838069382 }, "steps_from_proto": { "total": 92.66439770188026, "count": 63645, "is_parallel": true, "self": 19.731983583103556, "children": { "_process_rank_one_or_two_observation": { "total": 72.9324141187767, "count": 509160, "is_parallel": true, "self": 72.9324141187767 } } } } } } } } } } }, "trainer_advance": { "total": 606.1700968200144, "count": 63646, "self": 2.7035485379528836, "children": { "process_trajectory": { "total": 101.83620542506196, "count": 63646, "self": 101.6329930310626, "children": { "RLTrainer._checkpoint": { "total": 0.2032123939993653, "count": 2, "self": 0.2032123939993653 } } }, "_update_policy": { "total": 501.6303428569995, "count": 449, "self": 321.54123719402287, "children": { "TorchPPOOptimizer.update": { "total": 180.08910566297664, "count": 22767, "self": 180.08910566297664 } } } } } } }, "trainer_threads": { "total": 9.279992809752002e-07, "count": 1, "self": 9.279992809752002e-07 }, "TrainerController._save_models": { "total": 0.09485040999970806, "count": 1, "self": 0.0015772970000398345, "children": { "RLTrainer._checkpoint": { "total": 0.09327311299966823, "count": 1, "self": 0.09327311299966823 } } } } } } }