{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30211636424064636, "min": 0.30211636424064636, "max": 1.4908859729766846, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8889.4716796875, "min": 8889.4716796875, "max": 45227.515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989878.0, "min": 29954.0, "max": 989878.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989878.0, "min": 29954.0, "max": 989878.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6154250502586365, "min": -0.10308139026165009, "max": 0.6888172626495361, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.01156616210938, "min": -24.533370971679688, "max": 200.44581604003906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009412795305252075, "min": -0.0017550316406413913, "max": 0.31154927611351013, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.6920595169067383, "min": -0.46332836151123047, "max": 74.14872741699219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06432319990389737, "min": 0.06432319990389737, "max": 0.07449798169088483, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9005247986545631, "min": 0.5568000239025047, "max": 1.0429717436723875, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015712600044069058, "min": 0.0014082121376178278, "max": 0.016333975809863028, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21997640061696683, "min": 0.015490333513796105, "max": 0.24023094416685023, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4154332425071435e-06, "min": 7.4154332425071435e-06, "max": 0.00029476338924553746, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001038160653951, "min": 0.0001038160653951, "max": 0.0036324514891829, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247177857142857, "min": 0.10247177857142857, "max": 0.1982544625, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346049, "min": 1.4346049, "max": 2.6108171, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025693067928571437, "min": 0.00025693067928571437, "max": 0.00982562080375, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003597029510000001, "min": 0.003597029510000001, "max": 0.12110062829000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010655115358531475, "min": 0.010655115358531475, "max": 0.2111760377883911, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1491716206073761, "min": 0.1491716206073761, "max": 1.689408302307129, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.53, "min": 289.15238095238095, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29953.0, "min": 18415.0, "max": 31767.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6604659827053547, "min": -0.9999467184146246, "max": 1.6917923667601176, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 166.04659827053547, "min": -29.998401552438736, "max": 177.63819850981236, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6604659827053547, "min": -0.9999467184146246, "max": 1.6917923667601176, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 166.04659827053547, "min": -29.998401552438736, "max": 177.63819850981236, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03299005653727363, "min": 0.03275553709674915, "max": 5.25350645929575, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.299005653727363, "min": 3.299005653727363, "max": 99.81662272661924, "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": "1763328123", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/home/maksym/.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": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1763328952" }, "total": 828.6824313819961, "count": 1, "self": 0.21750725999299902, "children": { "run_training.setup": { "total": 0.026000189005571883, "count": 1, "self": 0.026000189005571883 }, "TrainerController.start_learning": { "total": 828.4389239329976, "count": 1, "self": 0.9233907795060077, "children": { "TrainerController._reset_env": { "total": 1.3853639609951642, "count": 1, "self": 1.3853639609951642 }, "TrainerController.advance": { "total": 826.087196182496, "count": 64199, "self": 0.8786253383004805, "children": { "env_step": { "total": 535.468913599645, "count": 64199, "self": 457.5027788160587, "children": { "SubprocessEnvManager._take_step": { "total": 77.38954473360354, "count": 64199, "self": 2.5972849114987184, "children": { "TorchPolicy.evaluate": { "total": 74.79225982210482, "count": 62549, "self": 74.79225982210482 } } }, "workers": { "total": 0.5765900499827694, "count": 64199, "self": 0.0, "children": { "worker_root": { "total": 827.3165136868265, "count": 64199, "is_parallel": true, "self": 426.31027968944545, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008640789965284057, "count": 1, "is_parallel": true, "self": 0.0002454269924783148, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006186520040500909, "count": 8, "is_parallel": true, "self": 0.0006186520040500909 } } }, "UnityEnvironment.step": { "total": 0.016458342004625592, "count": 1, "is_parallel": true, "self": 0.0002321250067325309, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016318399866577238, "count": 1, "is_parallel": true, "self": 0.00016318399866577238 }, "communicator.exchange": { "total": 0.015482340000744443, "count": 1, "is_parallel": true, "self": 0.015482340000744443 }, "steps_from_proto": { "total": 0.0005806929984828457, "count": 1, "is_parallel": true, "self": 0.00012382799468468875, "children": { "_process_rank_one_or_two_observation": { "total": 0.000456865003798157, "count": 8, "is_parallel": true, "self": 0.000456865003798157 } } } } } } }, "UnityEnvironment.step": { "total": 401.00623399738106, "count": 64198, "is_parallel": true, "self": 11.645591095606505, "children": { "UnityEnvironment._generate_step_input": { "total": 7.0408911654376425, "count": 64198, "is_parallel": true, "self": 7.0408911654376425 }, "communicator.exchange": { "total": 352.07890527614654, "count": 64198, "is_parallel": true, "self": 352.07890527614654 }, "steps_from_proto": { "total": 30.24084646019037, "count": 64198, "is_parallel": true, "self": 6.7891031775361625, "children": { "_process_rank_one_or_two_observation": { "total": 23.451743282654206, "count": 513584, "is_parallel": true, "self": 23.451743282654206 } } } } } } } } } } }, "trainer_advance": { "total": 289.7396572445505, "count": 64199, "self": 1.6342882080280106, "children": { "process_trajectory": { "total": 57.84619601747545, "count": 64199, "self": 57.740801752479456, "children": { "RLTrainer._checkpoint": { "total": 0.10539426499599358, "count": 2, "self": 0.10539426499599358 } } }, "_update_policy": { "total": 230.259173019047, "count": 460, "self": 132.52350621382357, "children": { "TorchPPOOptimizer.update": { "total": 97.73566680522345, "count": 22758, "self": 97.73566680522345 } } } } } } }, "trainer_threads": { "total": 5.269976099953055e-07, "count": 1, "self": 5.269976099953055e-07 }, "TrainerController._save_models": { "total": 0.04297248300281353, "count": 1, "self": 0.0005806090048281476, "children": { "RLTrainer._checkpoint": { "total": 0.042391873997985385, "count": 1, "self": 0.042391873997985385 } } } } } } }