{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.21211472153663635, "min": 0.1816847175359726, "max": 1.4950337409973145, "count": 60 }, "Pyramids.Policy.Entropy.sum": { "value": 6424.53076171875, "min": 5436.0068359375, "max": 45353.34375, "count": 60 }, "Pyramids.Step.mean": { "value": 1799961.0, "min": 29952.0, "max": 1799961.0, "count": 60 }, "Pyramids.Step.sum": { "value": 1799961.0, "min": 29952.0, "max": 1799961.0, "count": 60 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6575861573219299, "min": -0.1069599986076355, "max": 0.7868034839630127, "count": 60 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 188.06964111328125, "min": -25.777359008789062, "max": 234.46743774414062, "count": 60 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004033910576254129, "min": -0.021981757134199142, "max": 0.29415881633758545, "count": 60 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.153698444366455, "min": -6.352727890014648, "max": 69.71563720703125, "count": 60 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07202918340780719, "min": 0.06552136015393661, "max": 0.07682561214621773, "count": 60 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0804377511171077, "min": 0.5325852169181239, "max": 1.0928138651492476, "count": 60 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014569392515912506, "min": 0.0009376689546463589, "max": 0.017454386785781633, "count": 60 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2185408877386876, "min": 0.012189696410402667, "max": 0.24436141500094288, "count": 60 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001214983928338889, "min": 0.0001214983928338889, "max": 0.00029838354339596195, "count": 60 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0018224758925083333, "min": 0.001743836718721367, "max": 0.0040113516628828, "count": 60 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14049944444444445, "min": 0.14049944444444445, "max": 0.19946118095238097, "count": 60 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1074916666666668, "min": 1.3962282666666668, "max": 2.827521866666667, "count": 60 }, "Pyramids.Policy.Beta.mean": { "value": 0.0040558945, "min": 0.0040558945, "max": 0.009946171977142856, "count": 60 }, "Pyramids.Policy.Beta.sum": { "value": 0.06083841749999999, "min": 0.058209735469999996, "max": 0.13371800828, "count": 60 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008634376339614391, "min": 0.008634376339614391, "max": 0.389129102230072, "count": 60 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1295156478881836, "min": 0.12178749591112137, "max": 2.7239036560058594, "count": 60 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 270.16521739130434, "min": 231.3153846153846, "max": 999.0, "count": 60 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31069.0, "min": 15984.0, "max": 33265.0, "count": 60 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.729834763381792, "min": -1.0000000521540642, "max": 1.768062976518954, "count": 60 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 198.9309977889061, "min": -28.90560158342123, "max": 227.92879781126976, "count": 60 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.729834763381792, "min": -1.0000000521540642, "max": 1.768062976518954, "count": 60 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 198.9309977889061, "min": -28.90560158342123, "max": 227.92879781126976, "count": 60 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02405205868189628, "min": 0.021907024710694365, "max": 7.563969396054745, "count": 60 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7659867484180722, "min": 2.6379935412551276, "max": 121.02351033687592, "count": 60 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686144236", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "1686148446" }, "total": 4210.70768014, "count": 1, "self": 0.8015624670006218, "children": { "run_training.setup": { "total": 0.04126253000003999, "count": 1, "self": 0.04126253000003999 }, "TrainerController.start_learning": { "total": 4209.864855143, "count": 1, "self": 2.4639892420409524, "children": { "TrainerController._reset_env": { "total": 4.403764655000032, "count": 1, "self": 4.403764655000032 }, "TrainerController.advance": { "total": 4202.762149711959, "count": 118157, "self": 2.476035407094969, "children": { "env_step": { "total": 3060.5881256049115, "count": 118157, "self": 2865.3354584750145, "children": { "SubprocessEnvManager._take_step": { "total": 193.79227397992827, "count": 118157, "self": 8.601374512937355, "children": { "TorchPolicy.evaluate": { "total": 185.1908994669909, "count": 114129, "self": 185.1908994669909 } } }, "workers": { "total": 1.460393149968695, "count": 118157, "self": 0.0, "children": { "worker_root": { "total": 4199.437702158983, "count": 118157, "is_parallel": true, "self": 1538.4832066119943, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017499670000233891, "count": 1, "is_parallel": true, "self": 0.0005663779998030805, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011835890002203087, "count": 8, "is_parallel": true, "self": 0.0011835890002203087 } } }, "UnityEnvironment.step": { "total": 0.07886772699998801, "count": 1, "is_parallel": true, "self": 0.0005370100002437539, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004668909998599702, "count": 1, "is_parallel": true, "self": 0.0004668909998599702 }, "communicator.exchange": { "total": 0.07593581599985555, "count": 1, "is_parallel": true, "self": 0.07593581599985555 }, "steps_from_proto": { "total": 0.0019280100000287348, "count": 1, "is_parallel": true, "self": 0.0004063760002281924, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015216339998005424, "count": 8, "is_parallel": true, "self": 0.0015216339998005424 } } } } } } }, "UnityEnvironment.step": { "total": 2660.9544955469883, "count": 118156, "is_parallel": true, "self": 58.01293884583811, "children": { "UnityEnvironment._generate_step_input": { "total": 43.03889656905744, "count": 118156, "is_parallel": true, "self": 43.03889656905744 }, "communicator.exchange": { "total": 2382.021012825058, "count": 118156, "is_parallel": true, "self": 2382.021012825058 }, "steps_from_proto": { "total": 177.88164730703443, "count": 118156, "is_parallel": true, "self": 36.345930130344186, "children": { "_process_rank_one_or_two_observation": { "total": 141.53571717669024, "count": 945248, "is_parallel": true, "self": 141.53571717669024 } } } } } } } } } } }, "trainer_advance": { "total": 1139.6979886999527, "count": 118157, "self": 4.868962189911144, "children": { "process_trajectory": { "total": 195.87262642304745, "count": 118157, "self": 195.5797480120475, "children": { "RLTrainer._checkpoint": { "total": 0.29287841099994694, "count": 3, "self": 0.29287841099994694 } } }, "_update_policy": { "total": 938.9564000869941, "count": 846, "self": 605.1213207659684, "children": { "TorchPPOOptimizer.update": { "total": 333.83507932102566, "count": 41641, "self": 333.83507932102566 } } } } } } }, "trainer_threads": { "total": 1.2370001059025526e-06, "count": 1, "self": 1.2370001059025526e-06 }, "TrainerController._save_models": { "total": 0.23495029700006853, "count": 1, "self": 0.001834442000472336, "children": { "RLTrainer._checkpoint": { "total": 0.2331158549995962, "count": 1, "self": 0.2331158549995962 } } } } } } }