{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4364183247089386, "min": 0.4364183247089386, "max": 1.3196464776992798, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12952.8955078125, "min": 12952.8955078125, "max": 40032.796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989889.0, "min": 29900.0, "max": 989889.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989889.0, "min": 29900.0, "max": 989889.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.39364901185035706, "min": -0.15100909769535065, "max": 0.41996756196022034, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 106.28523254394531, "min": -35.78915786743164, "max": 113.39124298095703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.029679453000426292, "min": -0.029679453000426292, "max": 0.35827627778053284, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.013452529907227, "min": -8.013452529907227, "max": 87.0611343383789, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0681851870380342, "min": 0.06478606916956554, "max": 0.07543013763343223, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.022777805570513, "min": 0.5280109634340256, "max": 1.071900576973955, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015913735126378014, "min": 0.0008934209021942349, "max": 0.018448189659726007, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23870602689567022, "min": 0.011614471728525054, "max": 0.2582746552361641, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.576577474506669e-06, "min": 7.576577474506669e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011364866211760003, "min": 0.00011364866211760003, "max": 0.0035082497305834997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252549333333336, "min": 0.10252549333333336, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5378824000000004, "min": 1.3886848, "max": 2.5694165000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026229678400000004, "min": 0.00026229678400000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003934451760000001, "min": 0.003934451760000001, "max": 0.11696470835, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01663113385438919, "min": 0.016229888424277306, "max": 0.5719889998435974, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24946701526641846, "min": 0.22721843421459198, "max": 4.003922939300537, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 444.4925373134328, "min": 427.4714285714286, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29781.0, "min": 16827.0, "max": 33109.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4957850456460198, "min": -0.9999200517932574, "max": 1.4957850456460198, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 100.21759805828333, "min": -29.997601553797722, "max": 105.21799843013287, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4957850456460198, "min": -0.9999200517932574, "max": 1.4957850456460198, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 100.21759805828333, "min": -29.997601553797722, "max": 105.21799843013287, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07591465595803822, "min": 0.07591465595803822, "max": 10.387660105438794, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.08628194918856, "min": 5.08628194918856, "max": 176.5902217924595, "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": "1689682832", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689685289" }, "total": 2457.0226278630003, "count": 1, "self": 0.5260259930000757, "children": { "run_training.setup": { "total": 0.04456316000005245, "count": 1, "self": 0.04456316000005245 }, "TrainerController.start_learning": { "total": 2456.45203871, "count": 1, "self": 1.7596926980413627, "children": { "TrainerController._reset_env": { "total": 4.856784271000151, "count": 1, "self": 4.856784271000151 }, "TrainerController.advance": { "total": 2449.7368411139582, "count": 63518, "self": 1.848386117006612, "children": { "env_step": { "total": 1735.1779525079828, "count": 63518, "self": 1600.275293484918, "children": { "SubprocessEnvManager._take_step": { "total": 133.80329847807593, "count": 63518, "self": 5.4735015841133645, "children": { "TorchPolicy.evaluate": { "total": 128.32979689396257, "count": 62552, "self": 128.32979689396257 } } }, "workers": { "total": 1.09936054498894, "count": 63518, "self": 0.0, "children": { "worker_root": { "total": 2450.566689787935, "count": 63518, "is_parallel": true, "self": 985.1818190009344, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020937159999903088, "count": 1, "is_parallel": true, "self": 0.0006232149999050307, "children": { "_process_rank_one_or_two_observation": { "total": 0.001470501000085278, "count": 8, "is_parallel": true, "self": 0.001470501000085278 } } }, "UnityEnvironment.step": { "total": 0.0833203100000901, "count": 1, "is_parallel": true, "self": 0.0006282059998738987, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045959199997014366, "count": 1, "is_parallel": true, "self": 0.00045959199997014366 }, "communicator.exchange": { "total": 0.08028509700011455, "count": 1, "is_parallel": true, "self": 0.08028509700011455 }, "steps_from_proto": { "total": 0.0019474150001315138, "count": 1, "is_parallel": true, "self": 0.00038080100034676434, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015666139997847495, "count": 8, "is_parallel": true, "self": 0.0015666139997847495 } } } } } } }, "UnityEnvironment.step": { "total": 1465.3848707870006, "count": 63517, "is_parallel": true, "self": 38.93920957700084, "children": { "UnityEnvironment._generate_step_input": { "total": 25.597454306067675, "count": 63517, "is_parallel": true, "self": 25.597454306067675 }, "communicator.exchange": { "total": 1279.9858864999517, "count": 63517, "is_parallel": true, "self": 1279.9858864999517 }, "steps_from_proto": { "total": 120.86232040398045, "count": 63517, "is_parallel": true, "self": 23.86798548109732, "children": { "_process_rank_one_or_two_observation": { "total": 96.99433492288313, "count": 508136, "is_parallel": true, "self": 96.99433492288313 } } } } } } } } } } }, "trainer_advance": { "total": 712.7105024889688, "count": 63518, "self": 3.267680451985825, "children": { "process_trajectory": { "total": 120.27048939998394, "count": 63518, "self": 120.04189057598387, "children": { "RLTrainer._checkpoint": { "total": 0.22859882400007336, "count": 2, "self": 0.22859882400007336 } } }, "_update_policy": { "total": 589.172332636999, "count": 454, "self": 381.09204814003147, "children": { "TorchPPOOptimizer.update": { "total": 208.08028449696758, "count": 22800, "self": 208.08028449696758 } } } } } } }, "trainer_threads": { "total": 1.2210002751089633e-06, "count": 1, "self": 1.2210002751089633e-06 }, "TrainerController._save_models": { "total": 0.09871940599987283, "count": 1, "self": 0.0014949119995435467, "children": { "RLTrainer._checkpoint": { "total": 0.09722449400032929, "count": 1, "self": 0.09722449400032929 } } } } } } }