{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0188018083572388, "min": 1.0188018083572388, "max": 1.4814026355743408, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 30515.15234375, "min": 30515.15234375, "max": 44939.83203125, "count": 3 }, "Pyramids.Step.mean": { "value": 89897.0, "min": 29975.0, "max": 89897.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89897.0, "min": 29975.0, "max": 89897.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07936542481184006, "min": -0.17528338730335236, "max": -0.07936542481184006, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -19.12706756591797, "min": -41.717445373535156, "max": -19.12706756591797, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1228138655424118, "min": 0.1228138655424118, "max": 0.2524747848510742, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 29.598140716552734, "min": 29.598140716552734, "max": 60.0890007019043, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0712435307308123, "min": 0.06850825346092108, "max": 0.07249792377210806, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9261658995005598, "min": 0.5074854664047564, "max": 0.9261658995005598, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0017534098856690687, "min": 0.0017534098856690687, "max": 0.004709439305010349, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.022794328513697892, "min": 0.022794328513697892, "max": 0.0452753760948104, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.572422860476921e-05, "min": 7.572422860476921e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0009844149718619998, "min": 0.0009844149718619998, "max": 0.0019674575441810003, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12524138461538462, "min": 0.12524138461538462, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.628138, "min": 1.2868480000000002, "max": 1.855819, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.002531614323076923, "min": 0.002531614323076923, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.0329109862, "min": 0.0329109862, "max": 0.0656363181, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.08811005204916, "min": 0.08811005204916, "max": 0.31133005023002625, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.1454306840896606, "min": 1.1454306840896606, "max": 2.1793103218078613, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 991.625, "min": 958.9411764705883, "max": 991.625, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31732.0, "min": 16774.0, "max": 32604.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8674750525970012, "min": -0.8700000485953163, "max": -0.7245176971396979, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -27.75920168310404, "min": -27.75920168310404, "max": -14.790000826120377, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8674750525970012, "min": -0.8700000485953163, "max": -0.7245176971396979, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -27.75920168310404, "min": -27.75920168310404, "max": -14.790000826120377, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 0.9801330148475245, "min": 0.9801330148475245, "max": 6.044643790844609, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 31.364256475120783, "min": 31.364256475120783, "max": 102.75894444435835, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1780344344", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1780344559" }, "total": 214.932443445, "count": 1, "self": 0.4808614570001737, "children": { "run_training.setup": { "total": 0.022835621000012907, "count": 1, "self": 0.022835621000012907 }, "TrainerController.start_learning": { "total": 214.4287463669998, "count": 1, "self": 0.13084990305560495, "children": { "TrainerController._reset_env": { "total": 2.193858179000017, "count": 1, "self": 2.193858179000017 }, "TrainerController.advance": { "total": 211.99608948794412, "count": 6316, "self": 0.13376956795673323, "children": { "env_step": { "total": 145.80193447496004, "count": 6316, "self": 130.26702204399498, "children": { "SubprocessEnvManager._take_step": { "total": 15.456462868977724, "count": 6316, "self": 0.47049408095972467, "children": { "TorchPolicy.evaluate": { "total": 14.985968788017999, "count": 6303, "self": 14.985968788017999 } } }, "workers": { "total": 0.07844956198732689, "count": 6316, "self": 0.0, "children": { "worker_root": { "total": 213.7848134499509, "count": 6316, "is_parallel": true, "self": 95.09129380295326, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002101048999975319, "count": 1, "is_parallel": true, "self": 0.0006965219999983674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014045269999769516, "count": 8, "is_parallel": true, "self": 0.0014045269999769516 } } }, "UnityEnvironment.step": { "total": 0.052567302999705134, "count": 1, "is_parallel": true, "self": 0.0005690020007023122, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004995509998479974, "count": 1, "is_parallel": true, "self": 0.0004995509998479974 }, "communicator.exchange": { "total": 0.04963096299979952, "count": 1, "is_parallel": true, "self": 0.04963096299979952 }, "steps_from_proto": { "total": 0.0018677869993553031, "count": 1, "is_parallel": true, "self": 0.00037687900112359785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014909079982317053, "count": 8, "is_parallel": true, "self": 0.0014909079982317053 } } } } } } }, "UnityEnvironment.step": { "total": 118.69351964699763, "count": 6315, "is_parallel": true, "self": 3.414096788020288, "children": { "UnityEnvironment._generate_step_input": { "total": 2.3695646429923727, "count": 6315, "is_parallel": true, "self": 2.3695646429923727 }, "communicator.exchange": { "total": 101.83674765195155, "count": 6315, "is_parallel": true, "self": 101.83674765195155 }, "steps_from_proto": { "total": 11.073110564033414, "count": 6315, "is_parallel": true, "self": 2.305956688972401, "children": { "_process_rank_one_or_two_observation": { "total": 8.767153875061013, "count": 50520, "is_parallel": true, "self": 8.767153875061013 } } } } } } } } } } }, "trainer_advance": { "total": 66.06038544502735, "count": 6316, "self": 0.17513866199806216, "children": { "process_trajectory": { "total": 12.307471895027447, "count": 6316, "self": 12.307471895027447 }, "_update_policy": { "total": 53.57777488800184, "count": 36, "self": 29.78163769099592, "children": { "TorchPPOOptimizer.update": { "total": 23.79613719700592, "count": 2274, "self": 23.79613719700592 } } } } } } }, "trainer_threads": { "total": 9.880004654405639e-07, "count": 1, "self": 9.880004654405639e-07 }, "TrainerController._save_models": { "total": 0.10794780899959733, "count": 1, "self": 0.0008784579995335662, "children": { "RLTrainer._checkpoint": { "total": 0.10706935100006376, "count": 1, "self": 0.10706935100006376 } } } } } } }