{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1579221934080124, "min": 0.14510126411914825, "max": 1.533879280090332, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4719.978515625, "min": 4343.75146484375, "max": 46531.76171875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999910.0, "min": 29952.0, "max": 2999910.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999910.0, "min": 29952.0, "max": 2999910.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8294655680656433, "min": -0.0951676070690155, "max": 0.8294655680656433, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 253.81646728515625, "min": -22.840225219726562, "max": 253.81646728515625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010292568244040012, "min": -0.005333239678293467, "max": 0.18681637942790985, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.1495258808135986, "min": -1.55197274684906, "max": 44.275482177734375, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06550295066885084, "min": 0.06454392184969038, "max": 0.07334582248070595, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9170413093639118, "min": 0.4852379330946735, "max": 1.0763609724429746, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01623626449023092, "min": 5.029978611167838e-05, "max": 0.01843072892340917, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22730770286323285, "min": 0.0007041970055634973, "max": 0.2764609338511375, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5644851928238055e-06, "min": 1.5644851928238055e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1902792699533277e-05, "min": 2.1902792699533277e-05, "max": 0.0038011433329522668, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052146190476188, "min": 0.10052146190476188, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073004666666664, "min": 1.3962282666666668, "max": 2.752530599999999, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.209404428571417e-05, "min": 6.209404428571417e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008693166199999984, "min": 0.0008693166199999984, "max": 0.12671806856, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006671026349067688, "min": 0.0064842673018574715, "max": 0.3140048086643219, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09339436888694763, "min": 0.09077974408864975, "max": 2.198033571243286, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 213.44525547445255, "min": 213.44525547445255, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29242.0, "min": 15984.0, "max": 32622.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7719532724497091, "min": -1.0000000521540642, "max": 1.7801804349834758, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 242.75759832561016, "min": -31.998401656746864, "max": 242.75759832561016, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7719532724497091, "min": -1.0000000521540642, "max": 1.7801804349834758, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 242.75759832561016, "min": -31.998401656746864, "max": 242.75759832561016, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014865801145044754, "min": 0.014865801145044754, "max": 6.276421092450619, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0366147568711312, "min": 1.9764109910611296, "max": 100.4227374792099, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710147010", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710157719" }, "total": 10709.155112024, "count": 1, "self": 0.8003637969995907, "children": { "run_training.setup": { "total": 0.07530831799977022, "count": 1, "self": 0.07530831799977022 }, "TrainerController.start_learning": { "total": 10708.279439909, "count": 1, "self": 6.9676022791536525, "children": { "TrainerController._reset_env": { "total": 3.5440687630002685, "count": 1, "self": 3.5440687630002685 }, "TrainerController.advance": { "total": 10697.672549592846, "count": 194509, "self": 7.659661154477362, "children": { "env_step": { "total": 7502.739210424131, "count": 194509, "self": 7002.834698072715, "children": { "SubprocessEnvManager._take_step": { "total": 495.398511127818, "count": 194509, "self": 21.672477296742727, "children": { "TorchPolicy.evaluate": { "total": 473.72603383107526, "count": 187546, "self": 473.72603383107526 } } }, "workers": { "total": 4.506001223598105, "count": 194509, "self": 0.0, "children": { "worker_root": { "total": 10687.27904807896, "count": 194509, "is_parallel": true, "self": 4266.6229689618285, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007486625000183267, "count": 1, "is_parallel": true, "self": 0.005098195000755368, "children": { "_process_rank_one_or_two_observation": { "total": 0.002388429999427899, "count": 8, "is_parallel": true, "self": 0.002388429999427899 } } }, "UnityEnvironment.step": { "total": 0.06394270100008725, "count": 1, "is_parallel": true, "self": 0.0007952240002850886, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000618290000147681, "count": 1, "is_parallel": true, "self": 0.000618290000147681 }, "communicator.exchange": { "total": 0.06050593999998455, "count": 1, "is_parallel": true, "self": 0.06050593999998455 }, "steps_from_proto": { "total": 0.0020232469996699365, "count": 1, "is_parallel": true, "self": 0.00042478700015635695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015984599995135795, "count": 8, "is_parallel": true, "self": 0.0015984599995135795 } } } } } } }, "UnityEnvironment.step": { "total": 6420.656079117132, "count": 194508, "is_parallel": true, "self": 155.26222282852723, "children": { "UnityEnvironment._generate_step_input": { "total": 84.74629514395292, "count": 194508, "is_parallel": true, "self": 84.74629514395292 }, "communicator.exchange": { "total": 5770.670792277714, "count": 194508, "is_parallel": true, "self": 5770.670792277714 }, "steps_from_proto": { "total": 409.9767688669385, "count": 194508, "is_parallel": true, "self": 88.30697931015175, "children": { "_process_rank_one_or_two_observation": { "total": 321.6697895567868, "count": 1556064, "is_parallel": true, "self": 321.6697895567868 } } } } } } } } } } }, "trainer_advance": { "total": 3187.2736780142377, "count": 194509, "self": 15.60351623401175, "children": { "process_trajectory": { "total": 506.7601542382522, "count": 194509, "self": 505.9913493242525, "children": { "RLTrainer._checkpoint": { "total": 0.768804913999702, "count": 6, "self": 0.768804913999702 } } }, "_update_policy": { "total": 2664.9100075419738, "count": 1388, "self": 1084.0077478438293, "children": { "TorchPPOOptimizer.update": { "total": 1580.9022596981445, "count": 68340, "self": 1580.9022596981445 } } } } } } }, "trainer_threads": { "total": 1.1400006769690663e-06, "count": 1, "self": 1.1400006769690663e-06 }, "TrainerController._save_models": { "total": 0.09521813399987877, "count": 1, "self": 0.0025635220008553006, "children": { "RLTrainer._checkpoint": { "total": 0.09265461199902347, "count": 1, "self": 0.09265461199902347 } } } } } } }