{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5059620141983032, "min": 0.5059620141983032, "max": 1.4305322170257568, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15089.810546875, "min": 15089.810546875, "max": 43396.625, "count": 33 }, "Pyramids.Step.mean": { "value": 989937.0, "min": 29999.0, "max": 989937.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989937.0, "min": 29999.0, "max": 989937.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4249880313873291, "min": -0.09896979480981827, "max": 0.4249880313873291, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 113.4718017578125, "min": -23.95069122314453, "max": 113.4718017578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007189627271145582, "min": -0.012300923466682434, "max": 0.23620356619358063, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.919630527496338, "min": -3.259744644165039, "max": 56.21644973754883, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07148924073442772, "min": 0.0672560162777544, "max": 0.0741673887724046, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.000849370281988, "min": 0.5154024187614105, "max": 1.057683193038407, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014268743769553976, "min": 0.0004955920466051994, "max": 0.014268743769553976, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19976241277375567, "min": 0.006938288652472792, "max": 0.19976241277375567, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.427518952764288e-06, "min": 7.427518952764288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010398526533870003, "min": 0.00010398526533870003, "max": 0.0033839600720134, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247580714285713, "min": 0.10247580714285713, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346613, "min": 1.3886848, "max": 2.5279866, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002573331335714287, "min": 0.0002573331335714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036026638700000016, "min": 0.0036026638700000016, "max": 0.11282586133999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005479026585817337, "min": 0.005315556190907955, "max": 0.27529478073120117, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07670637220144272, "min": 0.07441778481006622, "max": 1.9270634651184082, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 429.1641791044776, "min": 429.1641791044776, "max": 994.1212121212121, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28754.0, "min": 16798.0, "max": 33012.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4513969856189257, "min": -0.9156312993727624, "max": 1.4640253713679692, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 97.24359803646803, "min": -29.300201579928398, "max": 97.24359803646803, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4513969856189257, "min": -0.9156312993727624, "max": 1.4640253713679692, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 97.24359803646803, "min": -29.300201579928398, "max": 97.24359803646803, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025319945710926637, "min": 0.025319945710926637, "max": 6.743852309444371, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6964363626320846, "min": 1.6964363626320846, "max": 114.64548926055431, "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": "1701607772", "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": "1701610849" }, "total": 3076.8765478780006, "count": 1, "self": 0.4846083689990337, "children": { "run_training.setup": { "total": 0.06364610200034804, "count": 1, "self": 0.06364610200034804 }, "TrainerController.start_learning": { "total": 3076.328293407001, "count": 1, "self": 1.907808246289278, "children": { "TrainerController._reset_env": { "total": 3.3382981569993717, "count": 1, "self": 3.3382981569993717 }, "TrainerController.advance": { "total": 3070.957656363711, "count": 63482, "self": 1.9102471202713787, "children": { "env_step": { "total": 1727.1720158321277, "count": 63482, "self": 1559.5132922311623, "children": { "SubprocessEnvManager._take_step": { "total": 166.50244064216713, "count": 63482, "self": 5.866151534324672, "children": { "TorchPolicy.evaluate": { "total": 160.63628910784246, "count": 62553, "self": 160.63628910784246 } } }, "workers": { "total": 1.1562829587983288, "count": 63482, "self": 0.0, "children": { "worker_root": { "total": 3070.519298624098, "count": 63482, "is_parallel": true, "self": 1654.0215251453083, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021548280001297826, "count": 1, "is_parallel": true, "self": 0.0007255069995153463, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014293210006144363, "count": 8, "is_parallel": true, "self": 0.0014293210006144363 } } }, "UnityEnvironment.step": { "total": 0.05839411300075881, "count": 1, "is_parallel": true, "self": 0.0006738150004821364, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000556045000848826, "count": 1, "is_parallel": true, "self": 0.000556045000848826 }, "communicator.exchange": { "total": 0.055197730000145384, "count": 1, "is_parallel": true, "self": 0.055197730000145384 }, "steps_from_proto": { "total": 0.0019665229992824607, "count": 1, "is_parallel": true, "self": 0.00041922700074792374, "children": { "_process_rank_one_or_two_observation": { "total": 0.001547295998534537, "count": 8, "is_parallel": true, "self": 0.001547295998534537 } } } } } } }, "UnityEnvironment.step": { "total": 1416.49777347879, "count": 63481, "is_parallel": true, "self": 40.04335343177445, "children": { "UnityEnvironment._generate_step_input": { "total": 27.38011672997891, "count": 63481, "is_parallel": true, "self": 27.38011672997891 }, "communicator.exchange": { "total": 1237.3800697499428, "count": 63481, "is_parallel": true, "self": 1237.3800697499428 }, "steps_from_proto": { "total": 111.69423356709376, "count": 63481, "is_parallel": true, "self": 23.45300956322535, "children": { "_process_rank_one_or_two_observation": { "total": 88.24122400386841, "count": 507848, "is_parallel": true, "self": 88.24122400386841 } } } } } } } } } } }, "trainer_advance": { "total": 1341.875393411312, "count": 63482, "self": 3.479469573307142, "children": { "process_trajectory": { "total": 144.27931406601238, "count": 63482, "self": 144.0292230660125, "children": { "RLTrainer._checkpoint": { "total": 0.25009099999988393, "count": 2, "self": 0.25009099999988393 } } }, "_update_policy": { "total": 1194.1166097719924, "count": 452, "self": 691.6297224109367, "children": { "TorchPPOOptimizer.update": { "total": 502.4868873610558, "count": 45690, "self": 502.4868873610558 } } } } } } }, "trainer_threads": { "total": 1.0180010576732457e-06, "count": 1, "self": 1.0180010576732457e-06 }, "TrainerController._save_models": { "total": 0.12452962200040929, "count": 1, "self": 0.0023703480019321432, "children": { "RLTrainer._checkpoint": { "total": 0.12215927399847715, "count": 1, "self": 0.12215927399847715 } } } } } } }