{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37396812438964844, "min": 0.35487833619117737, "max": 1.388562560081482, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11213.060546875, "min": 10600.92578125, "max": 42123.43359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48766669631004333, "min": -0.09453216195106506, "max": 0.5691879391670227, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 133.1330108642578, "min": -22.87678337097168, "max": 158.6292724609375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006121527869254351, "min": -0.013367807492613792, "max": 0.41516491770744324, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.6711771488189697, "min": -3.5558369159698486, "max": 100.05474853515625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07090376969117082, "min": 0.06477456537384502, "max": 0.07433237115697967, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9926527756763914, "min": 0.5026972485084324, "max": 1.0563565355550963, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018013254034411844, "min": 0.00039397728644664613, "max": 0.018013254034411844, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2521855564817658, "min": 0.004727727437359754, "max": 0.26258950710568263, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3443332662071465e-06, "min": 7.3443332662071465e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010282066572690005, "min": 0.00010282066572690005, "max": 0.0035077682307439995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244807857142858, "min": 0.10244807857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342731000000002, "min": 1.3886848, "max": 2.569256, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002545630492857144, "min": 0.0002545630492857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035638826900000016, "min": 0.0035638826900000016, "max": 0.1169486744, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016161348670721054, "min": 0.015798252075910568, "max": 0.5014392137527466, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22625888884067535, "min": 0.22117552161216736, "max": 3.5100746154785156, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 353.7848101265823, "min": 325.3695652173913, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27949.0, "min": 15984.0, "max": 32424.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4916724832728505, "min": -1.0000000521540642, "max": 1.6003434574636428, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 119.33379866182804, "min": -31.998801678419113, "max": 150.45579826831818, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4916724832728505, "min": -1.0000000521540642, "max": 1.6003434574636428, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 119.33379866182804, "min": -31.998801678419113, "max": 150.45579826831818, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06110989575008716, "min": 0.05677495351839369, "max": 8.54308264888823, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.888791660006973, "min": 4.8817032291553915, "max": 136.68932238221169, "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": "1691183803", "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": "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": "1691186663" }, "total": 2859.401788855, "count": 1, "self": 0.5779864560004171, "children": { "run_training.setup": { "total": 0.06978898200009098, "count": 1, "self": 0.06978898200009098 }, "TrainerController.start_learning": { "total": 2858.7540134169994, "count": 1, "self": 2.049672840932544, "children": { "TrainerController._reset_env": { "total": 5.997426318999942, "count": 1, "self": 5.997426318999942 }, "TrainerController.advance": { "total": 2850.598419321067, "count": 63978, "self": 2.1461536860829256, "children": { "env_step": { "total": 2067.0116805579673, "count": 63978, "self": 1918.3123697629023, "children": { "SubprocessEnvManager._take_step": { "total": 147.46761372606397, "count": 63978, "self": 5.936588883148261, "children": { "TorchPolicy.evaluate": { "total": 141.5310248429157, "count": 62555, "self": 141.5310248429157 } } }, "workers": { "total": 1.2316970690010294, "count": 63978, "self": 0.0, "children": { "worker_root": { "total": 2851.567753397999, "count": 63978, "is_parallel": true, "self": 1086.5822042040907, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002962299000046187, "count": 1, "is_parallel": true, "self": 0.0007808810005371924, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021814179995089944, "count": 8, "is_parallel": true, "self": 0.0021814179995089944 } } }, "UnityEnvironment.step": { "total": 0.05553555200003757, "count": 1, "is_parallel": true, "self": 0.000680489999922429, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005850370000644034, "count": 1, "is_parallel": true, "self": 0.0005850370000644034 }, "communicator.exchange": { "total": 0.05213647499999752, "count": 1, "is_parallel": true, "self": 0.05213647499999752 }, "steps_from_proto": { "total": 0.0021335500000532193, "count": 1, "is_parallel": true, "self": 0.0004041210004288587, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017294289996243606, "count": 8, "is_parallel": true, "self": 0.0017294289996243606 } } } } } } }, "UnityEnvironment.step": { "total": 1764.9855491939081, "count": 63977, "is_parallel": true, "self": 43.32807281470923, "children": { "UnityEnvironment._generate_step_input": { "total": 28.047772599076097, "count": 63977, "is_parallel": true, "self": 28.047772599076097 }, "communicator.exchange": { "total": 1559.3677246481082, "count": 63977, "is_parallel": true, "self": 1559.3677246481082 }, "steps_from_proto": { "total": 134.24197913201465, "count": 63977, "is_parallel": true, "self": 27.78225227808798, "children": { "_process_rank_one_or_two_observation": { "total": 106.45972685392667, "count": 511816, "is_parallel": true, "self": 106.45972685392667 } } } } } } } } } } }, "trainer_advance": { "total": 781.4405850770167, "count": 63978, "self": 3.5988050458993257, "children": { "process_trajectory": { "total": 133.91245692912094, "count": 63978, "self": 133.6052219841206, "children": { "RLTrainer._checkpoint": { "total": 0.30723494500034576, "count": 2, "self": 0.30723494500034576 } } }, "_update_policy": { "total": 643.9293231019965, "count": 450, "self": 421.32469216091295, "children": { "TorchPPOOptimizer.update": { "total": 222.60463094108354, "count": 22815, "self": 222.60463094108354 } } } } } } }, "trainer_threads": { "total": 1.1590000212891027e-06, "count": 1, "self": 1.1590000212891027e-06 }, "TrainerController._save_models": { "total": 0.10849377700014884, "count": 1, "self": 0.001664006000282825, "children": { "RLTrainer._checkpoint": { "total": 0.10682977099986601, "count": 1, "self": 0.10682977099986601 } } } } } } }