{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4385608434677124, "min": 0.4385608434677124, "max": 1.468900442123413, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13121.740234375, "min": 13121.740234375, "max": 44560.5625, "count": 33 }, "Pyramids.Step.mean": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989991.0, "min": 29952.0, "max": 989991.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45750945806503296, "min": -0.1090119406580925, "max": 0.5390098094940186, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 125.35758972167969, "min": -26.27187728881836, "max": 150.3837432861328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.007160266395658255, "min": -0.007160266395658255, "max": 0.32016846537590027, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.961912989616394, "min": -1.961912989616394, "max": 77.16059875488281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06855495640567304, "min": 0.06528624760056943, "max": 0.07325063565596272, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9597693896794226, "min": 0.4987990216756154, "max": 1.0945039698757075, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01752035361626616, "min": 0.00019777005220077042, "max": 0.018043880928969743, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24528495062772623, "min": 0.001779930469806934, "max": 0.25727580272359774, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.22726901951429e-06, "min": 7.22726901951429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010118176627320006, "min": 0.00010118176627320006, "max": 0.0032532305155898995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10240905714285717, "min": 0.10240905714285717, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337268000000003, "min": 1.3886848, "max": 2.4432944000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002506648085714287, "min": 0.0002506648085714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003509307320000002, "min": 0.003509307320000002, "max": 0.10846256899000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010820357128977776, "min": 0.010283890180289745, "max": 0.5441190600395203, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15148499608039856, "min": 0.14397446811199188, "max": 3.808833599090576, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 361.34939759036143, "min": 358.4642857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29992.0, "min": 15984.0, "max": 32776.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5475341237899733, "min": -1.0000000521540642, "max": 1.585624070232173, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.89779815077782, "min": -31.999601677060127, "max": 131.60679782927036, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5475341237899733, "min": -1.0000000521540642, "max": 1.585624070232173, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.89779815077782, "min": -31.999601677060127, "max": 131.60679782927036, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04035142379303224, "min": 0.039413529932582084, "max": 11.144240820780396, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.308816751028644, "min": 3.1156501553195994, "max": 178.30785313248634, "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": "1718988144", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718990311" }, "total": 2167.176694365, "count": 1, "self": 0.4921320140001626, "children": { "run_training.setup": { "total": 0.06233138100014912, "count": 1, "self": 0.06233138100014912 }, "TrainerController.start_learning": { "total": 2166.6222309699997, "count": 1, "self": 1.4083736140150904, "children": { "TrainerController._reset_env": { "total": 3.255442801000072, "count": 1, "self": 3.255442801000072 }, "TrainerController.advance": { "total": 2161.8733166789843, "count": 63760, "self": 1.4589870750164664, "children": { "env_step": { "total": 1519.5866968980033, "count": 63760, "self": 1383.4252293968736, "children": { "SubprocessEnvManager._take_step": { "total": 135.3013215520839, "count": 63760, "self": 4.644758076062772, "children": { "TorchPolicy.evaluate": { "total": 130.65656347602112, "count": 62551, "self": 130.65656347602112 } } }, "workers": { "total": 0.8601459490457728, "count": 63760, "self": 0.0, "children": { "worker_root": { "total": 2161.9619267230096, "count": 63760, "is_parallel": true, "self": 900.3352112850209, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007773674999953073, "count": 1, "is_parallel": true, "self": 0.006361931999663284, "children": { "_process_rank_one_or_two_observation": { "total": 0.001411743000289789, "count": 8, "is_parallel": true, "self": 0.001411743000289789 } } }, "UnityEnvironment.step": { "total": 0.05364162299997588, "count": 1, "is_parallel": true, "self": 0.0007030690001101902, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048737299994172645, "count": 1, "is_parallel": true, "self": 0.00048737299994172645 }, "communicator.exchange": { "total": 0.05053546899989669, "count": 1, "is_parallel": true, "self": 0.05053546899989669 }, "steps_from_proto": { "total": 0.0019157120000272698, "count": 1, "is_parallel": true, "self": 0.0004000669996457873, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015156450003814825, "count": 8, "is_parallel": true, "self": 0.0015156450003814825 } } } } } } }, "UnityEnvironment.step": { "total": 1261.6267154379887, "count": 63759, "is_parallel": true, "self": 34.56105366397401, "children": { "UnityEnvironment._generate_step_input": { "total": 23.039174472992727, "count": 63759, "is_parallel": true, "self": 23.039174472992727 }, "communicator.exchange": { "total": 1106.8353107520206, "count": 63759, "is_parallel": true, "self": 1106.8353107520206 }, "steps_from_proto": { "total": 97.19117654900128, "count": 63759, "is_parallel": true, "self": 19.563184297131556, "children": { "_process_rank_one_or_two_observation": { "total": 77.62799225186973, "count": 510072, "is_parallel": true, "self": 77.62799225186973 } } } } } } } } } } }, "trainer_advance": { "total": 640.8276327059646, "count": 63760, "self": 2.5893604440186664, "children": { "process_trajectory": { "total": 127.63646837694182, "count": 63760, "self": 127.364661094942, "children": { "RLTrainer._checkpoint": { "total": 0.27180728199982696, "count": 2, "self": 0.27180728199982696 } } }, "_update_policy": { "total": 510.6018038850041, "count": 443, "self": 300.1273326079902, "children": { "TorchPPOOptimizer.update": { "total": 210.4744712770139, "count": 22791, "self": 210.4744712770139 } } } } } } }, "trainer_threads": { "total": 9.560003491060343e-07, "count": 1, "self": 9.560003491060343e-07 }, "TrainerController._save_models": { "total": 0.08509692000006908, "count": 1, "self": 0.0013050640000074054, "children": { "RLTrainer._checkpoint": { "total": 0.08379185600006167, "count": 1, "self": 0.08379185600006167 } } } } } } }