{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17186559736728668, "min": 0.17186559736728668, "max": 1.482001543045044, "count": 91 }, "Pyramids.Policy.Entropy.sum": { "value": 5048.7236328125, "min": 5048.7236328125, "max": 44958.0, "count": 91 }, "Pyramids.Step.mean": { "value": 2729934.0, "min": 29977.0, "max": 2729934.0, "count": 91 }, "Pyramids.Step.sum": { "value": 2729934.0, "min": 29977.0, "max": 2729934.0, "count": 91 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7860856056213379, "min": -0.0887129083275795, "max": 0.7912559509277344, "count": 91 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 231.10916137695312, "min": -21.29109764099121, "max": 235.79428100585938, "count": 91 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004692904185503721, "min": -0.009491439908742905, "max": 0.33292362093925476, "count": 91 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3797138929367065, "min": -2.7620089054107666, "max": 79.90167236328125, "count": 91 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06698137825532328, "min": 0.06462487416103527, "max": 0.07437627378760521, "count": 91 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9377392955745261, "min": 0.5097825181323916, "max": 1.0831466284591942, "count": 91 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012834380085613314, "min": 0.00046492488100300955, "max": 0.017212455121463997, "count": 91 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1796813211985864, "min": 0.006508948334042134, "max": 0.2581868268219599, "count": 91 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.843987623435715e-05, "min": 2.843987623435715e-05, "max": 0.00029838354339596195, "count": 91 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0003981582672810001, "min": 0.0003981582672810001, "max": 0.004011818662727133, "count": 91 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10947992857142859, "min": 0.10947992857142859, "max": 0.19946118095238097, "count": 91 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5327190000000002, "min": 1.3962282666666668, "max": 2.7974854999999996, "count": 91 }, "Pyramids.Policy.Beta.mean": { "value": 0.0009570448642857146, "min": 0.0009570448642857146, "max": 0.009946171977142856, "count": 91 }, "Pyramids.Policy.Beta.sum": { "value": 0.013398628100000004, "min": 0.013398628100000004, "max": 0.13373355938, "count": 91 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00747219892218709, "min": 0.007383912336081266, "max": 0.5500368475914001, "count": 91 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10461078584194183, "min": 0.10337477177381516, "max": 3.8502578735351562, "count": 91 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 236.96581196581195, "min": 233.66666666666666, "max": 987.0909090909091, "count": 91 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27725.0, "min": 17671.0, "max": 33618.0, "count": 91 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7288324718928745, "min": -0.9273576273611097, "max": 1.7640319920778273, "count": 91 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 202.2733992114663, "min": -30.602801702916622, "max": 232.11519767343998, "count": 91 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7288324718928745, "min": -0.9273576273611097, "max": 1.7640319920778273, "count": 91 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 202.2733992114663, "min": -30.602801702916622, "max": 232.11519767343998, "count": 91 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018422305505846143, "min": 0.018422305505846143, "max": 9.840691762665907, "count": 91 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1554097441839986, "min": 2.1554097441839986, "max": 177.13245172798634, "count": 91 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 91 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 91 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684860911", "python_version": "3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0]", "command_line_arguments": "/home/alex/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1684863675" }, "total": 2763.385850223999, "count": 1, "self": 0.2914562819987623, "children": { "run_training.setup": { "total": 0.009183610000036424, "count": 1, "self": 0.009183610000036424 }, "TrainerController.start_learning": { "total": 2763.0852103320003, "count": 1, "self": 3.176989705439155, "children": { "TrainerController._reset_env": { "total": 5.94651264300046, "count": 1, "self": 5.94651264300046 }, "TrainerController.advance": { "total": 2753.8835655165603, "count": 177404, "self": 3.1563610572457037, "children": { "env_step": { "total": 1737.209295276135, "count": 177404, "self": 1523.059045614782, "children": { "SubprocessEnvManager._take_step": { "total": 212.05296071137582, "count": 177405, "self": 7.763149665605852, "children": { "TorchPolicy.evaluate": { "total": 204.28981104576997, "count": 171733, "self": 204.28981104576997 } } }, "workers": { "total": 2.0972889499771554, "count": 177403, "self": 0.0, "children": { "worker_root": { "total": 5514.382593989946, "count": 177403, "is_parallel": true, "self": 4171.159638423042, "children": { "run_training.setup": { "total": 0.009183610000036424, "count": 1, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008906069997465238, "count": 1, "is_parallel": true, "self": 0.00025540699880366446, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006352000009428593, "count": 8, "is_parallel": true, "self": 0.0006352000009428593 } } }, "UnityEnvironment.step": { "total": 0.0252248659999168, "count": 1, "is_parallel": true, "self": 0.00022188300044945208, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021399199977167882, "count": 1, "is_parallel": true, "self": 0.00021399199977167882 }, "communicator.exchange": { "total": 0.024060554999778105, "count": 1, "is_parallel": true, "self": 0.024060554999778105 }, "steps_from_proto": { "total": 0.0007284359999175649, "count": 1, "is_parallel": true, "self": 0.0001806069994927384, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005478290004248265, "count": 8, "is_parallel": true, "self": 0.0005478290004248265 } } } } } } }, "UnityEnvironment.step": { "total": 1343.2137719569037, "count": 177401, "is_parallel": true, "self": 39.57784843442005, "children": { "UnityEnvironment._generate_step_input": { "total": 29.08640164127064, "count": 177401, "is_parallel": true, "self": 29.08640164127064 }, "communicator.exchange": { "total": 1157.981323408574, "count": 177401, "is_parallel": true, "self": 1157.981323408574 }, "steps_from_proto": { "total": 116.56819847263887, "count": 177401, "is_parallel": true, "self": 28.561778727790625, "children": { "_process_rank_one_or_two_observation": { "total": 88.00641974484824, "count": 1419208, "is_parallel": true, "self": 88.00641974484824 } } } } }, "TrainerController.start_learning": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "TrainerController._reset_env": { "total": 5.94651264300046, "count": 1, "is_parallel": true, "self": 5.94651264300046 }, "TrainerController.advance": { "total": 2745.83086010857, "count": 177102, "is_parallel": true, "self": 3.1507737282872768, "children": { "env_step": { "total": 1730.062750791104, "count": 177102, "is_parallel": true, "self": 1516.2573878807416, "children": { "SubprocessEnvManager._take_step": { "total": 211.6855177423904, "count": 177103, "is_parallel": true, "self": 7.74973504463469, "children": { "TorchPolicy.evaluate": { "total": 203.9357826977557, "count": 171441, "is_parallel": true, "self": 203.9357826977557 } } }, "workers": { "total": 2.093629663972024, "count": 177102, "is_parallel": true, "self": 0.0, "children": { "worker_root": { "total": 2751.378265110947, "count": 177102, "is_parallel": true, "self": 1410.900371704056, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008906069997465238, "count": 1, "is_parallel": true, "self": 0.00025540699880366446, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006352000009428593, "count": 8, "is_parallel": true, "self": 0.0006352000009428593 } } }, "UnityEnvironment.step": { "total": 0.0252248659999168, "count": 1, "is_parallel": true, "self": 0.00022188300044945208, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021399199977167882, "count": 1, "is_parallel": true, "self": 0.00021399199977167882 }, "communicator.exchange": { "total": 0.024060554999778105, "count": 1, "is_parallel": true, "self": 0.024060554999778105 }, "steps_from_proto": { "total": 0.0007284359999175649, "count": 1, "is_parallel": true, "self": 0.0001806069994927384, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005478290004248265, "count": 8, "is_parallel": true, "self": 0.0005478290004248265 } } } } } } }, "UnityEnvironment.step": { "total": 1340.4778934068909, "count": 177101, "is_parallel": true, "self": 39.501118980394494, "children": { "UnityEnvironment._generate_step_input": { "total": 29.035699766260223, "count": 177101, "is_parallel": true, "self": 29.035699766260223 }, "communicator.exchange": { "total": 1155.5831629235872, "count": 177101, "is_parallel": true, "self": 1155.5831629235872 }, "steps_from_proto": { "total": 116.35791173664893, "count": 177101, "is_parallel": true, "self": 28.511636260799605, "children": { "_process_rank_one_or_two_observation": { "total": 87.84627547584932, "count": 1416808, "is_parallel": true, "self": 87.84627547584932 } } } } } } } } }, "steps_from_proto": { "total": 0.0009739399993122788, "count": 1, "is_parallel": true, "self": 0.00025128799825324677, "children": { "_process_rank_one_or_two_observation": { "total": 0.000722652001059032, "count": 8, "is_parallel": true, "self": 0.000722652001059032 } } }, "UnityEnvironment.step": { "total": 0.025241564000680228, "count": 1, "is_parallel": true, "self": 0.0003220389990019612, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018019100025412627, "count": 1, "is_parallel": true, "self": 0.00018019100025412627 }, "communicator.exchange": { "total": 0.023988468001334695, "count": 1, "is_parallel": true, "self": 0.023988468001334695 }, "steps_from_proto": { "total": 0.0007508660000894452, "count": 1, "is_parallel": true, "self": 0.0001755800003593322, "children": { "_process_rank_one_or_two_observation": { "total": 0.000575285999730113, "count": 8, "is_parallel": true, "self": 0.000575285999730113 } } } } } } }, "trainer_advance": { "total": 1012.6173355891788, "count": 177102, "is_parallel": true, "self": 5.725832465434905, "children": { "process_trajectory": { "total": 170.50902366075024, "count": 177102, "is_parallel": true, "self": 170.16315586575092, "children": { "RLTrainer._checkpoint": { "total": 0.34586779499932163, "count": 5, "is_parallel": true, "self": 0.34586779499932163 } } }, "_update_policy": { "total": 836.3824794629936, "count": 1281, "is_parallel": true, "self": 506.4192423470022, "children": { "TorchPPOOptimizer.update": { "total": 329.96323711599143, "count": 62448, "is_parallel": true, "self": 329.96323711599143 } } } } } } } } } } } } } } }, "trainer_advance": { "total": 1013.5179091831797, "count": 177403, "self": 5.73335654845414, "children": { "process_trajectory": { "total": 170.7628468967323, "count": 177403, "self": 170.41697910173298, "children": { "RLTrainer._checkpoint": { "total": 0.34586779499932163, "count": 5, "self": 0.34586779499932163 } } }, "_update_policy": { "total": 837.0217057379932, "count": 1282, "self": 506.80675195500135, "children": { "TorchPPOOptimizer.update": { "total": 330.21495378299187, "count": 62496, "self": 330.21495378299187 } } } } } } }, "trainer_threads": { "total": 2.4450000637443736e-06, "count": 1, "self": 2.4450000637443736e-06 }, "TrainerController._save_models": { "total": 0.0781400220002979, "count": 1, "self": 0.0007878129999880912, "children": { "RLTrainer._checkpoint": { "total": 0.07735220900030981, "count": 1, "self": 0.07735220900030981 } } } } } } }