{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2128964066505432, "min": 0.21030749380588531, "max": 1.5014017820358276, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6417.54931640625, "min": 6352.96875, "max": 45546.5234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29939.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29939.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.31374651193618774, "min": -0.08951158821582794, "max": 0.31374651193618774, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 81.5740966796875, "min": -21.66180419921875, "max": 81.5740966796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004393260460346937, "min": -0.012115906924009323, "max": 0.23532558977603912, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.1422476768493652, "min": -3.1380198001861572, "max": 56.47814178466797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06752732259199201, "min": 0.06522106252393847, "max": 0.07279608260828112, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9453825162878882, "min": 0.5798006398301124, "max": 1.0843246984683599, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012615614256425206, "min": 0.0011345364677769788, "max": 0.012615614256425206, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17661859958995288, "min": 0.015883510548877704, "max": 0.17661859958995288, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.41896895561429e-06, "min": 7.41896895561429e-06, "max": 0.0002948414642195125, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010386556537860007, "min": 0.00010386556537860007, "max": 0.003634944488351899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247295714285716, "min": 0.10247295714285716, "max": 0.1982804875, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346214000000002, "min": 1.4346214000000002, "max": 2.6116481, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002570484185714287, "min": 0.0002570484185714287, "max": 0.009828220701250001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035986778600000024, "min": 0.0035986778600000024, "max": 0.12118364519000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008793679997324944, "min": 0.008624312467873096, "max": 0.30082982778549194, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12311152368783951, "min": 0.12224704027175903, "max": 2.4066386222839355, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 510.0175438596491, "min": 510.0175438596491, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29071.0, "min": 16482.0, "max": 33890.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1038982205485042, "min": -0.9999750521965325, "max": 1.1683428294158407, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 62.922198571264744, "min": -31.99920167028904, "max": 65.42719844728708, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1038982205485042, "min": -0.9999750521965325, "max": 1.1683428294158407, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 62.922198571264744, "min": -31.99920167028904, "max": 65.42719844728708, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04689537300784427, "min": 0.04689537300784427, "max": 6.564111180165234, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6730362614471233, "min": 2.656817455776036, "max": 111.58989006280899, "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": "1700217974", "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": "1700220260" }, "total": 2285.5228324429995, "count": 1, "self": 0.43572933299901706, "children": { "run_training.setup": { "total": 0.04166331700025694, "count": 1, "self": 0.04166331700025694 }, "TrainerController.start_learning": { "total": 2285.0454397930002, "count": 1, "self": 1.5995892299156367, "children": { "TrainerController._reset_env": { "total": 4.784148884999922, "count": 1, "self": 4.784148884999922 }, "TrainerController.advance": { "total": 2278.586472650084, "count": 63598, "self": 1.7262340438956016, "children": { "env_step": { "total": 1625.3484271650227, "count": 63598, "self": 1480.2039698739654, "children": { "SubprocessEnvManager._take_step": { "total": 144.18083631203308, "count": 63598, "self": 4.871128785942801, "children": { "TorchPolicy.evaluate": { "total": 139.30970752609028, "count": 62570, "self": 139.30970752609028 } } }, "workers": { "total": 0.9636209790241992, "count": 63598, "self": 0.0, "children": { "worker_root": { "total": 2279.820372581928, "count": 63598, "is_parallel": true, "self": 930.9025903088218, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002430161999654956, "count": 1, "is_parallel": true, "self": 0.0006677939982182579, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017623680014366983, "count": 8, "is_parallel": true, "self": 0.0017623680014366983 } } }, "UnityEnvironment.step": { "total": 0.05362268099997891, "count": 1, "is_parallel": true, "self": 0.0005593279997810896, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005006799997318012, "count": 1, "is_parallel": true, "self": 0.0005006799997318012 }, "communicator.exchange": { "total": 0.04883407600027567, "count": 1, "is_parallel": true, "self": 0.04883407600027567 }, "steps_from_proto": { "total": 0.003728597000190348, "count": 1, "is_parallel": true, "self": 0.0003880680005750037, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033405289996153442, "count": 8, "is_parallel": true, "self": 0.0033405289996153442 } } } } } } }, "UnityEnvironment.step": { "total": 1348.9177822731062, "count": 63597, "is_parallel": true, "self": 35.88211202110733, "children": { "UnityEnvironment._generate_step_input": { "total": 26.179195308036924, "count": 63597, "is_parallel": true, "self": 26.179195308036924 }, "communicator.exchange": { "total": 1181.33779482701, "count": 63597, "is_parallel": true, "self": 1181.33779482701 }, "steps_from_proto": { "total": 105.51868011695205, "count": 63597, "is_parallel": true, "self": 22.222502548862394, "children": { "_process_rank_one_or_two_observation": { "total": 83.29617756808966, "count": 508776, "is_parallel": true, "self": 83.29617756808966 } } } } } } } } } } }, "trainer_advance": { "total": 651.5118114411657, "count": 63598, "self": 3.1603776352335444, "children": { "process_trajectory": { "total": 129.76795496093155, "count": 63598, "self": 129.5387627909322, "children": { "RLTrainer._checkpoint": { "total": 0.22919216999935088, "count": 2, "self": 0.22919216999935088 } } }, "_update_policy": { "total": 518.5834788450006, "count": 457, "self": 308.4481009559704, "children": { "TorchPPOOptimizer.update": { "total": 210.13537788903022, "count": 22767, "self": 210.13537788903022 } } } } } } }, "trainer_threads": { "total": 9.960003808373585e-07, "count": 1, "self": 9.960003808373585e-07 }, "TrainerController._save_models": { "total": 0.07522803200026829, "count": 1, "self": 0.0012851960009356844, "children": { "RLTrainer._checkpoint": { "total": 0.0739428359993326, "count": 1, "self": 0.0739428359993326 } } } } } } }