{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4501535892486572, "min": 0.4486143887042999, "max": 1.4560518264770508, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13483.0, "min": 13483.0, "max": 44170.7890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.25777995586395264, "min": -0.11794789880514145, "max": 0.31320255994796753, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 66.5072250366211, "min": -28.3074951171875, "max": 81.74586486816406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019375670701265335, "min": -0.015309936366975307, "max": 0.4058866798877716, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.998922824859619, "min": -3.9346537590026855, "max": 96.19514465332031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06749197908729988, "min": 0.06524749006604276, "max": 0.07308152839391432, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9448877072221984, "min": 0.5025228011340235, "max": 1.032751477780574, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008861512363893338, "min": 0.0008609545715377744, "max": 0.010425268980809447, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12406117309450672, "min": 0.007499160665404282, "max": 0.14662729072676717, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.638440311028571e-06, "min": 7.638440311028571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010693816435439999, "min": 0.00010693816435439999, "max": 0.0035084633305122997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254611428571427, "min": 0.10254611428571427, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356455999999997, "min": 1.3691136000000002, "max": 2.5694877000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002643568171428572, "min": 0.0002643568171428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037009954400000007, "min": 0.0037009954400000007, "max": 0.11697182123, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012626931071281433, "min": 0.012626931071281433, "max": 0.43533629179000854, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17677703499794006, "min": 0.17677703499794006, "max": 3.047353982925415, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 551.3571428571429, "min": 551.3571428571429, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30876.0, "min": 15984.0, "max": 33439.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0199714020958968, "min": -1.0000000521540642, "max": 1.190349968283304, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 57.118398517370224, "min": -32.000001668930054, "max": 66.65959822386503, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0199714020958968, "min": -1.0000000521540642, "max": 1.190349968283304, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 57.118398517370224, "min": -32.000001668930054, "max": 66.65959822386503, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07079909426517718, "min": 0.07079909426517718, "max": 9.17613117955625, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.964749278849922, "min": 3.839894669421483, "max": 146.8180988729, "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": "1668319556", "python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1668321563" }, "total": 2006.920354146, "count": 1, "self": 0.4404122070000085, "children": { "run_training.setup": { "total": 0.04320368300000155, "count": 1, "self": 0.04320368300000155 }, "TrainerController.start_learning": { "total": 2006.436738256, "count": 1, "self": 1.3603458889697322, "children": { "TrainerController._reset_env": { "total": 9.271001155000022, "count": 1, "self": 9.271001155000022 }, "TrainerController.advance": { "total": 1995.7145668780306, "count": 63438, "self": 1.4288642680444354, "children": { "env_step": { "total": 1280.0333347499914, "count": 63438, "self": 1173.4757702210286, "children": { "SubprocessEnvManager._take_step": { "total": 105.84180878100449, "count": 63438, "self": 4.593348875012282, "children": { "TorchPolicy.evaluate": { "total": 101.2484599059922, "count": 62562, "self": 34.72461992201215, "children": { "TorchPolicy.sample_actions": { "total": 66.52383998398005, "count": 62562, "self": 66.52383998398005 } } } } }, "workers": { "total": 0.7157557479581556, "count": 63438, "self": 0.0, "children": { "worker_root": { "total": 2002.0878044009958, "count": 63438, "is_parallel": true, "self": 930.9138011039975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005227834000038456, "count": 1, "is_parallel": true, "self": 0.0038131190000854076, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014147149999530484, "count": 8, "is_parallel": true, "self": 0.0014147149999530484 } } }, "UnityEnvironment.step": { "total": 0.04565710700001091, "count": 1, "is_parallel": true, "self": 0.00046872900003336326, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005513840000048731, "count": 1, "is_parallel": true, "self": 0.0005513840000048731 }, "communicator.exchange": { "total": 0.043093240000018795, "count": 1, "is_parallel": true, "self": 0.043093240000018795 }, "steps_from_proto": { "total": 0.0015437539999538785, "count": 1, "is_parallel": true, "self": 0.00042712300000857795, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011166309999453006, "count": 8, "is_parallel": true, "self": 0.0011166309999453006 } } } } } } }, "UnityEnvironment.step": { "total": 1071.1740032969983, "count": 63437, "is_parallel": true, "self": 27.759180619974813, "children": { "UnityEnvironment._generate_step_input": { "total": 22.955924445993162, "count": 63437, "is_parallel": true, "self": 22.955924445993162 }, "communicator.exchange": { "total": 918.2264233620054, "count": 63437, "is_parallel": true, "self": 918.2264233620054 }, "steps_from_proto": { "total": 102.23247486902483, "count": 63437, "is_parallel": true, "self": 23.247823464022133, "children": { "_process_rank_one_or_two_observation": { "total": 78.9846514050027, "count": 507496, "is_parallel": true, "self": 78.9846514050027 } } } } } } } } } } }, "trainer_advance": { "total": 714.2523678599948, "count": 63438, "self": 2.4537939740328056, "children": { "process_trajectory": { "total": 160.68994860696398, "count": 63438, "self": 160.48965634196384, "children": { "RLTrainer._checkpoint": { "total": 0.20029226500014374, "count": 2, "self": 0.20029226500014374 } } }, "_update_policy": { "total": 551.108625278998, "count": 446, "self": 220.17375921499746, "children": { "TorchPPOOptimizer.update": { "total": 330.9348660640006, "count": 22818, "self": 330.9348660640006 } } } } } } }, "trainer_threads": { "total": 1.1449997145973612e-06, "count": 1, "self": 1.1449997145973612e-06 }, "TrainerController._save_models": { "total": 0.09082318899982056, "count": 1, "self": 0.0016658429999552027, "children": { "RLTrainer._checkpoint": { "total": 0.08915734599986536, "count": 1, "self": 0.08915734599986536 } } } } } } }