{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2595840096473694, "min": 0.2595840096473694, "max": 1.429888129234314, "count": 43 }, "Pyramids.Policy.Entropy.sum": { "value": 7775.06005859375, "min": 7775.06005859375, "max": 43377.0859375, "count": 43 }, "Pyramids.Step.mean": { "value": 1289919.0, "min": 29952.0, "max": 1289919.0, "count": 43 }, "Pyramids.Step.sum": { "value": 1289919.0, "min": 29952.0, "max": 1289919.0, "count": 43 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6985498070716858, "min": -0.09293777495622635, "max": 0.7059111595153809, "count": 43 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 199.08670043945312, "min": -22.305065155029297, "max": 199.08670043945312, "count": 43 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011057536117732525, "min": -0.016626974567770958, "max": 0.24694859981536865, "count": 43 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.151397705078125, "min": -4.688807010650635, "max": 59.51461410522461, "count": 43 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06989851642029257, "min": 0.06480001986363075, "max": 0.07377321542767647, "count": 43 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.978579229884096, "min": 0.47993122830106505, "max": 1.087658801404805, "count": 43 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01419782695351188, "min": 0.00021845130944385052, "max": 0.01695324845024429, "count": 43 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19876957734916634, "min": 0.0030583183322139074, "max": 0.23864951169925203, "count": 43 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00017257802104543569, "min": 0.00017257802104543569, "max": 0.00029838354339596195, "count": 43 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0024160922946360997, "min": 0.0020886848037717336, "max": 0.004011134662955134, "count": 43 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15752599285714286, "min": 0.15752599285714286, "max": 0.19946118095238097, "count": 43 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2053639, "min": 1.3962282666666668, "max": 2.7975655333333336, "count": 43 }, "Pyramids.Policy.Beta.mean": { "value": 0.005756846686428571, "min": 0.005756846686428571, "max": 0.009946171977142856, "count": 43 }, "Pyramids.Policy.Beta.sum": { "value": 0.08059585360999999, "min": 0.06962320384, "max": 0.13371078218000002, "count": 43 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007949981838464737, "min": 0.007949981838464737, "max": 0.39310508966445923, "count": 43 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11129974573850632, "min": 0.11129974573850632, "max": 2.7517356872558594, "count": 43 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 297.12380952380954, "min": 282.20952380952383, "max": 999.0, "count": 43 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31198.0, "min": 15984.0, "max": 33185.0, "count": 43 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.645710459067708, "min": -1.0000000521540642, "max": 1.678729503992058, "count": 43 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 172.79959820210934, "min": -30.99280159920454, "max": 176.2665979191661, "count": 43 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.645710459067708, "min": -1.0000000521540642, "max": 1.678729503992058, "count": 43 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 172.79959820210934, "min": -30.99280159920454, "max": 176.2665979191661, "count": 43 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024484664773141655, "min": 0.024317557121893124, "max": 7.484507032670081, "count": 43 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5708898011798738, "min": 2.525750037704711, "max": 119.75211252272129, "count": 43 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 43 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 43 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1754502435", "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": "1754505312" }, "total": 2876.337038794, "count": 1, "self": 0.35499077600024975, "children": { "run_training.setup": { "total": 0.021552236000047742, "count": 1, "self": 0.021552236000047742 }, "TrainerController.start_learning": { "total": 2875.9604957819997, "count": 1, "self": 1.5919666889863038, "children": { "TrainerController._reset_env": { "total": 2.1537735599999905, "count": 1, "self": 2.1537735599999905 }, "TrainerController.advance": { "total": 2872.0913611250135, "count": 83266, "self": 1.5976625869948293, "children": { "env_step": { "total": 2026.6283384440167, "count": 83266, "self": 1848.0279787520258, "children": { "SubprocessEnvManager._take_step": { "total": 177.66731010896672, "count": 83266, "self": 5.637100571953965, "children": { "TorchPolicy.evaluate": { "total": 172.03020953701275, "count": 81122, "self": 172.03020953701275 } } }, "workers": { "total": 0.9330495830242853, "count": 83265, "self": 0.0, "children": { "worker_root": { "total": 2870.3070211610275, "count": 83265, "is_parallel": true, "self": 1158.5170522360452, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017454829999223875, "count": 1, "is_parallel": true, "self": 0.0005809110000427609, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011645719998796267, "count": 8, "is_parallel": true, "self": 0.0011645719998796267 } } }, "UnityEnvironment.step": { "total": 0.04872751400000652, "count": 1, "is_parallel": true, "self": 0.0005371550000745628, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043929399998887675, "count": 1, "is_parallel": true, "self": 0.00043929399998887675 }, "communicator.exchange": { "total": 0.046201644000007036, "count": 1, "is_parallel": true, "self": 0.046201644000007036 }, "steps_from_proto": { "total": 0.0015494209999360464, "count": 1, "is_parallel": true, "self": 0.0003397919999770238, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012096289999590226, "count": 8, "is_parallel": true, "self": 0.0012096289999590226 } } } } } } }, "UnityEnvironment.step": { "total": 1711.7899689249823, "count": 83264, "is_parallel": true, "self": 40.23711251396617, "children": { "UnityEnvironment._generate_step_input": { "total": 28.3635279829889, "count": 83264, "is_parallel": true, "self": 28.3635279829889 }, "communicator.exchange": { "total": 1524.9805671430422, "count": 83264, "is_parallel": true, "self": 1524.9805671430422 }, "steps_from_proto": { "total": 118.20876128498503, "count": 83264, "is_parallel": true, "self": 23.061378423049405, "children": { "_process_rank_one_or_two_observation": { "total": 95.14738286193563, "count": 666112, "is_parallel": true, "self": 95.14738286193563 } } } } } } } } } } }, "trainer_advance": { "total": 843.865360094002, "count": 83265, "self": 3.0935446770075714, "children": { "process_trajectory": { "total": 158.3030767569927, "count": 83265, "self": 157.98516524999275, "children": { "RLTrainer._checkpoint": { "total": 0.3179115069999625, "count": 2, "self": 0.3179115069999625 } } }, "_update_policy": { "total": 682.4687386600017, "count": 596, "self": 380.5375473930321, "children": { "TorchPPOOptimizer.update": { "total": 301.93119126696956, "count": 29544, "self": 301.93119126696956 } } } } } } }, "trainer_threads": { "total": 1.3389999367063865e-06, "count": 1, "self": 1.3389999367063865e-06 }, "TrainerController._save_models": { "total": 0.12339306900003066, "count": 1, "self": 0.0018807430001288594, "children": { "RLTrainer._checkpoint": { "total": 0.1215123259999018, "count": 1, "self": 0.1215123259999018 } } } } } } }