{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.216837540268898, "min": 0.216837540268898, "max": 1.1439133882522583, "count": 47 }, "Pyramids.Policy.Entropy.sum": { "value": 6591.861328125, "min": 1884.1458740234375, "max": 34317.40234375, "count": 47 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 47 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 47 }, "Pyramids.Step.mean": { "value": 1499974.0, "min": 149892.0, "max": 1499974.0, "count": 46 }, "Pyramids.Step.sum": { "value": 1499974.0, "min": 149892.0, "max": 1499974.0, "count": 46 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5635429620742798, "min": -0.1073768362402916, "max": 0.623300313949585, "count": 46 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.6097412109375, "min": -25.98519515991211, "max": 177.64059448242188, "count": 46 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0032277165446430445, "min": -0.05295085161924362, "max": 0.07620299607515335, "count": 46 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.9198992252349854, "min": -14.08492660522461, "max": 18.060110092163086, "count": 46 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06717732886456708, "min": 0.06439270613191184, "max": 0.0735065735864949, "count": 46 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.940482604103939, "min": 0.583830917285167, "max": 1.067276163356534, "count": 46 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01711601288081424, "min": 0.0011009482281105403, "max": 0.018873407717587217, "count": 46 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23962418033139937, "min": 0.015413275193547564, "max": 0.28310111576380825, "count": 46 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.8645276166190494e-06, "min": 2.8645276166190494e-06, "max": 0.000272566884144375, "count": 46 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.010338663266669e-05, "min": 4.010338663266669e-05, "max": 0.003569852210049334, "count": 46 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10095480952380953, "min": 0.10095480952380953, "max": 0.19085562500000003, "count": 46 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4133673333333334, "min": 1.4133673333333334, "max": 2.5899506666666667, "count": 46 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010538547142857148, "min": 0.00010538547142857148, "max": 0.009086476937499999, "count": 46 }, "Pyramids.Policy.Beta.sum": { "value": 0.0014753966000000008, "min": 0.0014753966000000008, "max": 0.1190160716, "count": 46 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007281546946614981, "min": 0.006628350354731083, "max": 0.061615318059921265, "count": 46 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10194166004657745, "min": 0.0965542420744896, "max": 0.6112106442451477, "count": 46 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 322.6326530612245, "min": 288.4271844660194, "max": 987.3333333333334, "count": 46 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31618.0, "min": 16326.0, "max": 33523.0, "count": 46 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5957163070537606, "min": -0.854693383226792, "max": 1.6708420864061306, "count": 46 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.38019809126854, "min": -27.840401589870453, "max": 170.28999785333872, "count": 46 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5957163070537606, "min": -0.854693383226792, "max": 1.6708420864061306, "count": 46 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.38019809126854, "min": -27.840401589870453, "max": 170.28999785333872, "count": 46 }, "Pyramids.Policy.RndReward.mean": { "value": 0.023973165170158312, "min": 0.022124219301162828, "max": 0.6562520817798727, "count": 46 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3493701866755146, "min": 1.954352687112987, "max": 18.973405182361603, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687291235", "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 --resume", "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": "1687294292" }, "total": 3056.8792389049995, "count": 1, "self": 0.7496070949996465, "children": { "run_training.setup": { "total": 0.03848574799985727, "count": 1, "self": 0.03848574799985727 }, "TrainerController.start_learning": { "total": 3056.091146062, "count": 1, "self": 1.6334947169725638, "children": { "TrainerController._reset_env": { "total": 3.9540592440000637, "count": 1, "self": 3.9540592440000637 }, "TrainerController.advance": { "total": 3050.414175517027, "count": 88556, "self": 1.6999190719966464, "children": { "env_step": { "total": 2206.4400515949983, "count": 88556, "self": 2065.3934808430704, "children": { "SubprocessEnvManager._take_step": { "total": 140.0602751009783, "count": 88556, "self": 6.13563863390732, "children": { "TorchPolicy.evaluate": { "total": 133.92463646707097, "count": 86323, "self": 133.92463646707097 } } }, "workers": { "total": 0.9862956509496144, "count": 88556, "self": 0.0, "children": { "worker_root": { "total": 3049.710723735973, "count": 88556, "is_parallel": true, "self": 1130.1138591509684, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027872109999407257, "count": 1, "is_parallel": true, "self": 0.0008003440002539719, "children": { "_process_rank_one_or_two_observation": { "total": 0.001986866999686754, "count": 8, "is_parallel": true, "self": 0.001986866999686754 } } }, "UnityEnvironment.step": { "total": 0.04545206300008431, "count": 1, "is_parallel": true, "self": 0.0005375059997732023, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000490628000079596, "count": 1, "is_parallel": true, "self": 0.000490628000079596 }, "communicator.exchange": { "total": 0.04279957100015963, "count": 1, "is_parallel": true, "self": 0.04279957100015963 }, "steps_from_proto": { "total": 0.0016243580000718794, "count": 1, "is_parallel": true, "self": 0.000359045000095648, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012653129999762314, "count": 8, "is_parallel": true, "self": 0.0012653129999762314 } } } } } } }, "UnityEnvironment.step": { "total": 1919.5968645850044, "count": 88555, "is_parallel": true, "self": 43.92660406803998, "children": { "UnityEnvironment._generate_step_input": { "total": 29.931304289943682, "count": 88555, "is_parallel": true, "self": 29.931304289943682 }, "communicator.exchange": { "total": 1712.2299676670234, "count": 88555, "is_parallel": true, "self": 1712.2299676670234 }, "steps_from_proto": { "total": 133.5089885599973, "count": 88555, "is_parallel": true, "self": 25.7646578750755, "children": { "_process_rank_one_or_two_observation": { "total": 107.7443306849218, "count": 708440, "is_parallel": true, "self": 107.7443306849218 } } } } } } } } } } }, "trainer_advance": { "total": 842.2742048500322, "count": 88556, "self": 3.339937450038633, "children": { "process_trajectory": { "total": 143.5362954599873, "count": 88556, "self": 143.24071930098762, "children": { "RLTrainer._checkpoint": { "total": 0.2955761589996655, "count": 3, "self": 0.2955761589996655 } } }, "_update_policy": { "total": 695.3979719400063, "count": 640, "self": 443.9013471990788, "children": { "TorchPPOOptimizer.update": { "total": 251.49662474092747, "count": 31458, "self": 251.49662474092747 } } } } } } }, "trainer_threads": { "total": 1.145000169344712e-06, "count": 1, "self": 1.145000169344712e-06 }, "TrainerController._save_models": { "total": 0.08941543899982207, "count": 1, "self": 0.0016526210001757136, "children": { "RLTrainer._checkpoint": { "total": 0.08776281799964636, "count": 1, "self": 0.08776281799964636 } } } } } } }