{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3466920554637909, "min": 0.32040712237358093, "max": 1.4239442348480225, "count": 36 }, "Pyramids.Policy.Entropy.sum": { "value": 10317.5556640625, "min": 9576.328125, "max": 43196.7734375, "count": 36 }, "Pyramids.Step.mean": { "value": 1079972.0, "min": 29952.0, "max": 1079972.0, "count": 36 }, "Pyramids.Step.sum": { "value": 1079972.0, "min": 29952.0, "max": 1079972.0, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5761666297912598, "min": -0.08735993504524231, "max": 0.6440982222557068, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.02198791503906, "min": -20.966384887695312, "max": 180.34750366210938, "count": 36 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.009499817155301571, "min": -0.02012954279780388, "max": 0.20657077431678772, "count": 36 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.6219494342803955, "min": -5.495365142822266, "max": 49.57698440551758, "count": 36 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06854505879649272, "min": 0.06710156514946859, "max": 0.07341465266472989, "count": 36 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9596308231508981, "min": 0.5101527830936421, "max": 1.0719401514312874, "count": 36 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014752796065988063, "min": 0.0002794324044564181, "max": 0.015930262425432114, "count": 36 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20653914492383288, "min": 0.0039120536623898534, "max": 0.2263247764931293, "count": 36 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019345482837221194, "min": 0.00019345482837221194, "max": 0.00029838354339596195, "count": 36 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002708367597210967, "min": 0.0020886848037717336, "max": 0.003969040076986666, "count": 36 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16448493095238095, "min": 0.16448493095238095, "max": 0.19946118095238097, "count": 36 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.302789033333333, "min": 1.3962282666666668, "max": 2.812459533333333, "count": 36 }, "Pyramids.Policy.Beta.mean": { "value": 0.006452044602142858, "min": 0.006452044602142858, "max": 0.009946171977142856, "count": 36 }, "Pyramids.Policy.Beta.sum": { "value": 0.09032862443, "min": 0.06962320384, "max": 0.132309032, "count": 36 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010192697867751122, "min": 0.009159141220152378, "max": 0.3912730813026428, "count": 36 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1426977664232254, "min": 0.12822797894477844, "max": 2.7389116287231445, "count": 36 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 320.36046511627904, "min": 295.5192307692308, "max": 999.0, "count": 36 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27551.0, "min": 15984.0, "max": 32959.0, "count": 36 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6331162610372831, "min": -1.0000000521540642, "max": 1.6622838488509577, "count": 36 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 140.44799844920635, "min": -31.995601683855057, "max": 169.40039839595556, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6331162610372831, "min": -1.0000000521540642, "max": 1.6622838488509577, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 140.44799844920635, "min": -31.995601683855057, "max": 169.40039839595556, "count": 36 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033614160975852174, "min": 0.02898731272008403, "max": 7.49978287704289, "count": 36 }, "Pyramids.Policy.RndReward.sum": { "value": 2.890817843923287, "min": 2.8712861785897985, "max": 119.99652603268623, "count": 36 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693146061", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1693148664" }, "total": 2602.670568202, "count": 1, "self": 0.5375249220005571, "children": { "run_training.setup": { "total": 0.04109233100007259, "count": 1, "self": 0.04109233100007259 }, "TrainerController.start_learning": { "total": 2602.0919509489995, "count": 1, "self": 1.8059071788934489, "children": { "TrainerController._reset_env": { "total": 5.260616505000144, "count": 1, "self": 5.260616505000144 }, "TrainerController.advance": { "total": 2595.022229628106, "count": 69698, "self": 1.8689473900390112, "children": { "env_step": { "total": 1852.5340761020727, "count": 69698, "self": 1718.7312522812076, "children": { "SubprocessEnvManager._take_step": { "total": 132.7208023339408, "count": 69698, "self": 5.585568335006883, "children": { "TorchPolicy.evaluate": { "total": 127.13523399893393, "count": 68033, "self": 127.13523399893393 } } }, "workers": { "total": 1.0820214869243046, "count": 69697, "self": 0.0, "children": { "worker_root": { "total": 2595.7121810468866, "count": 69697, "is_parallel": true, "self": 1015.3819638679151, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017461990000811056, "count": 1, "is_parallel": true, "self": 0.0005236380002315855, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012225609998495202, "count": 8, "is_parallel": true, "self": 0.0012225609998495202 } } }, "UnityEnvironment.step": { "total": 0.0950639410000349, "count": 1, "is_parallel": true, "self": 0.0006444719997489301, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048608500014779565, "count": 1, "is_parallel": true, "self": 0.00048608500014779565 }, "communicator.exchange": { "total": 0.0917997970000215, "count": 1, "is_parallel": true, "self": 0.0917997970000215 }, "steps_from_proto": { "total": 0.002133587000116677, "count": 1, "is_parallel": true, "self": 0.0004339039999194938, "children": { "_process_rank_one_or_two_observation": { "total": 0.001699683000197183, "count": 8, "is_parallel": true, "self": 0.001699683000197183 } } } } } } }, "UnityEnvironment.step": { "total": 1580.3302171789715, "count": 69696, "is_parallel": true, "self": 39.0403104181737, "children": { "UnityEnvironment._generate_step_input": { "total": 25.538884366981165, "count": 69696, "is_parallel": true, "self": 25.538884366981165 }, "communicator.exchange": { "total": 1393.5484745048898, "count": 69696, "is_parallel": true, "self": 1393.5484745048898 }, "steps_from_proto": { "total": 122.2025478889268, "count": 69696, "is_parallel": true, "self": 24.641722812845728, "children": { "_process_rank_one_or_two_observation": { "total": 97.56082507608107, "count": 557568, "is_parallel": true, "self": 97.56082507608107 } } } } } } } } } } }, "trainer_advance": { "total": 740.6192061359941, "count": 69697, "self": 3.3175967709548786, "children": { "process_trajectory": { "total": 125.88663414304688, "count": 69697, "self": 125.62123267904667, "children": { "RLTrainer._checkpoint": { "total": 0.26540146400020603, "count": 2, "self": 0.26540146400020603 } } }, "_update_policy": { "total": 611.4149752219923, "count": 493, "self": 399.62268989998097, "children": { "TorchPPOOptimizer.update": { "total": 211.79228532201137, "count": 24813, "self": 211.79228532201137 } } } } } } }, "trainer_threads": { "total": 1.5349996829172596e-06, "count": 1, "self": 1.5349996829172596e-06 }, "TrainerController._save_models": { "total": 0.003196102000401879, "count": 1, "self": 3.196500074409414e-05, "children": { "RLTrainer._checkpoint": { "total": 0.003164136999657785, "count": 1, "self": 0.003164136999657785 } } } } } } }