{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39134863018989563, "min": 0.3637741804122925, "max": 1.486986517906189, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11634.01171875, "min": 10895.7646484375, "max": 45109.22265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989916.0, "min": 29952.0, "max": 989916.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.607032835483551, "min": -0.0955917090177536, "max": 0.6449509859085083, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.18325805664062, "min": -22.9420108795166, "max": 185.8196258544922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030423590913414955, "min": -0.002952906768769026, "max": 0.36439648270606995, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.579452514648438, "min": -0.8386255502700806, "max": 86.36196899414062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0662976157930921, "min": 0.06595806034103949, "max": 0.07433332335559699, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9281666211032893, "min": 0.4990742157160535, "max": 1.0550762770118822, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01640917170042477, "min": 0.0013668381607521499, "max": 0.0168649423782245, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2297284038059468, "min": 0.01783660943274508, "max": 0.2529741356733675, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.537726058885711e-06, "min": 7.537726058885711e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010552816482439996, "min": 0.00010552816482439996, "max": 0.0037589257470247994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251254285714285, "min": 0.10251254285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351756, "min": 1.3886848, "max": 2.6529752, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002610030314285714, "min": 0.0002610030314285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036540424399999992, "min": 0.0036540424399999992, "max": 0.12531222247999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009462259709835052, "min": 0.009462259709835052, "max": 0.3910942077636719, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13247163593769073, "min": 0.13247163593769073, "max": 2.737659454345703, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 324.319587628866, "min": 284.21, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31459.0, "min": 15984.0, "max": 33507.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6138041023280203, "min": -1.0000000521540642, "max": 1.7151333173116048, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.53899792581797, "min": -30.53700166940689, "max": 180.0889983177185, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6138041023280203, "min": -1.0000000521540642, "max": 1.7151333173116048, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.53899792581797, "min": -30.53700166940689, "max": 180.0889983177185, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03137797465159068, "min": 0.028816048964217772, "max": 8.006041097454727, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.043663541204296, "min": 2.881604896421777, "max": 128.09665755927563, "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": "1736549969", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736552186" }, "total": 2216.908312945, "count": 1, "self": 0.4867400019993511, "children": { "run_training.setup": { "total": 0.05325366000010945, "count": 1, "self": 0.05325366000010945 }, "TrainerController.start_learning": { "total": 2216.3683192830003, "count": 1, "self": 1.2666083670269472, "children": { "TrainerController._reset_env": { "total": 2.3577812419998736, "count": 1, "self": 2.3577812419998736 }, "TrainerController.advance": { "total": 2212.6544395279734, "count": 64085, "self": 1.3609327710473735, "children": { "env_step": { "total": 1527.8241139129468, "count": 64085, "self": 1383.5769176547976, "children": { "SubprocessEnvManager._take_step": { "total": 143.4941234340638, "count": 64085, "self": 4.3944586790221365, "children": { "TorchPolicy.evaluate": { "total": 139.09966475504166, "count": 62556, "self": 139.09966475504166 } } }, "workers": { "total": 0.7530728240853932, "count": 64085, "self": 0.0, "children": { "worker_root": { "total": 2211.7470555199748, "count": 64085, "is_parallel": true, "self": 940.0982835930149, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001966844999969908, "count": 1, "is_parallel": true, "self": 0.0006022629995641182, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013645820004057896, "count": 8, "is_parallel": true, "self": 0.0013645820004057896 } } }, "UnityEnvironment.step": { "total": 0.08016526000005797, "count": 1, "is_parallel": true, "self": 0.000623464999762291, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043995000009999785, "count": 1, "is_parallel": true, "self": 0.00043995000009999785 }, "communicator.exchange": { "total": 0.0772279590000835, "count": 1, "is_parallel": true, "self": 0.0772279590000835 }, "steps_from_proto": { "total": 0.0018738860001121793, "count": 1, "is_parallel": true, "self": 0.0005185720001463778, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013553139999658015, "count": 8, "is_parallel": true, "self": 0.0013553139999658015 } } } } } } }, "UnityEnvironment.step": { "total": 1271.6487719269599, "count": 64084, "is_parallel": true, "self": 31.882020634896207, "children": { "UnityEnvironment._generate_step_input": { "total": 22.820733035094463, "count": 64084, "is_parallel": true, "self": 22.820733035094463 }, "communicator.exchange": { "total": 1121.4598297200455, "count": 64084, "is_parallel": true, "self": 1121.4598297200455 }, "steps_from_proto": { "total": 95.48618853692369, "count": 64084, "is_parallel": true, "self": 19.137763000821224, "children": { "_process_rank_one_or_two_observation": { "total": 76.34842553610247, "count": 512672, "is_parallel": true, "self": 76.34842553610247 } } } } } } } } } } }, "trainer_advance": { "total": 683.469392843979, "count": 64085, "self": 2.451615199035132, "children": { "process_trajectory": { "total": 130.932128306943, "count": 64085, "self": 130.67876844494367, "children": { "RLTrainer._checkpoint": { "total": 0.2533598619993427, "count": 2, "self": 0.2533598619993427 } } }, "_update_policy": { "total": 550.0856493380008, "count": 455, "self": 311.3155813819635, "children": { "TorchPPOOptimizer.update": { "total": 238.77006795603734, "count": 22803, "self": 238.77006795603734 } } } } } } }, "trainer_threads": { "total": 9.509999472356867e-07, "count": 1, "self": 9.509999472356867e-07 }, "TrainerController._save_models": { "total": 0.08948919500016927, "count": 1, "self": 0.0016973379997580196, "children": { "RLTrainer._checkpoint": { "total": 0.08779185700041126, "count": 1, "self": 0.08779185700041126 } } } } } } }