{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36388111114501953, "min": 0.36082106828689575, "max": 1.3619272708892822, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10939.7216796875, "min": 10882.36328125, "max": 41315.42578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6870867013931274, "min": -0.14043697714805603, "max": 0.6870867013931274, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 193.75845336914062, "min": -33.84531021118164, "max": 195.73585510253906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.014113446697592735, "min": -0.014113446697592735, "max": 0.46571844816207886, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.979991912841797, "min": -3.979991912841797, "max": 110.37527465820312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0682737242639719, "min": 0.0652914140931088, "max": 0.0739880066711669, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9558321396956064, "min": 0.5179160466981683, "max": 1.0322897654465018, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015149859910750475, "min": 0.0006086442082104853, "max": 0.016328301463675286, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21209803875050665, "min": 0.0060864420821048525, "max": 0.22859622049145398, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3053332792071405e-06, "min": 7.3053332792071405e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010227466590889997, "min": 0.00010227466590889997, "max": 0.003508324430558599, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243507857142857, "min": 0.10243507857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340911, "min": 1.3886848, "max": 2.5694414, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025326434928571424, "min": 0.00025326434928571424, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035457008899999996, "min": 0.0035457008899999996, "max": 0.11696719585999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007993116043508053, "min": 0.007993116043508053, "max": 0.5264849066734314, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11190362274646759, "min": 0.11190362274646759, "max": 3.685394287109375, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 280.9622641509434, "min": 261.88695652173914, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29782.0, "min": 15984.0, "max": 34135.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7001660170982469, "min": -1.0000000521540642, "max": 1.7381130254786947, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 180.21759781241417, "min": -31.999601677060127, "max": 199.8829979300499, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7001660170982469, "min": -1.0000000521540642, "max": 1.7381130254786947, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 180.21759781241417, "min": -31.999601677060127, "max": 199.8829979300499, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.023254469431261863, "min": 0.022820179931042493, "max": 10.48137660883367, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4649737597137573, "min": 2.4649737597137573, "max": 167.70202574133873, "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": "1684158193", "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": "1684160355" }, "total": 2162.4289586020004, "count": 1, "self": 0.4244134390000909, "children": { "run_training.setup": { "total": 0.06016731299996536, "count": 1, "self": 0.06016731299996536 }, "TrainerController.start_learning": { "total": 2161.9443778500004, "count": 1, "self": 1.307585359024415, "children": { "TrainerController._reset_env": { "total": 4.3175737370002025, "count": 1, "self": 4.3175737370002025 }, "TrainerController.advance": { "total": 2156.226968955975, "count": 64085, "self": 1.3311984408401258, "children": { "env_step": { "total": 1531.5896159741164, "count": 64085, "self": 1426.2278611181791, "children": { "SubprocessEnvManager._take_step": { "total": 104.59646198097653, "count": 64085, "self": 4.505862787006208, "children": { "TorchPolicy.evaluate": { "total": 100.09059919397032, "count": 62571, "self": 100.09059919397032 } } }, "workers": { "total": 0.7652928749607781, "count": 64085, "self": 0.0, "children": { "worker_root": { "total": 2157.11519476903, "count": 64085, "is_parallel": true, "self": 838.8712793470422, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028519649999907415, "count": 1, "is_parallel": true, "self": 0.000811249999969732, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020407150000210095, "count": 8, "is_parallel": true, "self": 0.0020407150000210095 } } }, "UnityEnvironment.step": { "total": 0.046239481999691634, "count": 1, "is_parallel": true, "self": 0.0005807879992971721, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047882700027912506, "count": 1, "is_parallel": true, "self": 0.00047882700027912506 }, "communicator.exchange": { "total": 0.04332701900011671, "count": 1, "is_parallel": true, "self": 0.04332701900011671 }, "steps_from_proto": { "total": 0.0018528479999986303, "count": 1, "is_parallel": true, "self": 0.00039168199964478845, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014611660003538418, "count": 8, "is_parallel": true, "self": 0.0014611660003538418 } } } } } } }, "UnityEnvironment.step": { "total": 1318.2439154219878, "count": 64084, "is_parallel": true, "self": 30.796843358981732, "children": { "UnityEnvironment._generate_step_input": { "total": 22.441158486945824, "count": 64084, "is_parallel": true, "self": 22.441158486945824 }, "communicator.exchange": { "total": 1169.7127967740162, "count": 64084, "is_parallel": true, "self": 1169.7127967740162 }, "steps_from_proto": { "total": 95.2931168020441, "count": 64084, "is_parallel": true, "self": 19.29042830759181, "children": { "_process_rank_one_or_two_observation": { "total": 76.00268849445229, "count": 512672, "is_parallel": true, "self": 76.00268849445229 } } } } } } } } } } }, "trainer_advance": { "total": 623.3061545410183, "count": 64085, "self": 2.527593583030921, "children": { "process_trajectory": { "total": 103.82620703399198, "count": 64085, "self": 103.62186175999159, "children": { "RLTrainer._checkpoint": { "total": 0.2043452740003886, "count": 2, "self": 0.2043452740003886 } } }, "_update_policy": { "total": 516.9523539239954, "count": 449, "self": 331.9703770918977, "children": { "TorchPPOOptimizer.update": { "total": 184.98197683209764, "count": 22821, "self": 184.98197683209764 } } } } } } }, "trainer_threads": { "total": 1.0800004019984044e-06, "count": 1, "self": 1.0800004019984044e-06 }, "TrainerController._save_models": { "total": 0.09224871800051915, "count": 1, "self": 0.0013459670008160174, "children": { "RLTrainer._checkpoint": { "total": 0.09090275099970313, "count": 1, "self": 0.09090275099970313 } } } } } } }