{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3820152282714844, "min": 0.3820152282714844, "max": 1.4666264057159424, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11368.7734375, "min": 11368.7734375, "max": 44491.578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.25611087679862976, "min": -0.12301318347454071, "max": 0.34956738352775574, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 65.82049560546875, "min": -29.523164749145508, "max": 91.58665466308594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.001834269380196929, "min": -0.023266626521945, "max": 0.33336490392684937, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.4714072346687317, "min": -5.770123481750488, "max": 79.00748443603516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07096227088810078, "min": 0.06553525356682216, "max": 0.07096227088810078, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9934717924334109, "min": 0.4903418627589668, "max": 1.0208580700370173, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012679628994755191, "min": 0.0001545016771361885, "max": 0.012679628994755191, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17751480592657268, "min": 0.0020085218027704505, "max": 0.17751480592657268, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.748218845864285e-06, "min": 7.748218845864285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010847506384209999, "min": 0.00010847506384209999, "max": 0.0035070869309710992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258270714285715, "min": 0.10258270714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361579000000002, "min": 1.3886848, "max": 2.5690289, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002680124435714286, "min": 0.0002680124435714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037521742100000005, "min": 0.0037521742100000005, "max": 0.11692598710999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009253355674445629, "min": 0.009253355674445629, "max": 0.39021825790405273, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12954698503017426, "min": 0.12954698503017426, "max": 2.731527805328369, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 512.4150943396227, "min": 512.4150943396227, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27158.0, "min": 15984.0, "max": 33443.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.221056581808711, "min": -1.0000000521540642, "max": 1.2985962571369276, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.71599883586168, "min": -31.996801659464836, "max": 70.1241978853941, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.221056581808711, "min": -1.0000000521540642, "max": 1.2985962571369276, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.71599883586168, "min": -31.996801659464836, "max": 70.1241978853941, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.051189134826549805, "min": 0.051189134826549805, "max": 7.553069240413606, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7130241458071396, "min": 2.7130241458071396, "max": 120.8491078466177, "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": "1741166240", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741168257" }, "total": 2017.88542349, "count": 1, "self": 0.7554275860002235, "children": { "run_training.setup": { "total": 0.02074958899993362, "count": 1, "self": 0.02074958899993362 }, "TrainerController.start_learning": { "total": 2017.1092463149998, "count": 1, "self": 1.2199819169354669, "children": { "TrainerController._reset_env": { "total": 2.9051937799999905, "count": 1, "self": 2.9051937799999905 }, "TrainerController.advance": { "total": 2012.8544029680638, "count": 63438, "self": 1.2583063030915582, "children": { "env_step": { "total": 1340.4768093739594, "count": 63438, "self": 1194.8666227060462, "children": { "SubprocessEnvManager._take_step": { "total": 144.87512884797934, "count": 63438, "self": 4.4101793239246945, "children": { "TorchPolicy.evaluate": { "total": 140.46494952405465, "count": 62550, "self": 140.46494952405465 } } }, "workers": { "total": 0.7350578199338997, "count": 63438, "self": 0.0, "children": { "worker_root": { "total": 2012.5331406260839, "count": 63438, "is_parallel": true, "self": 920.3807351721093, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025614420001147664, "count": 1, "is_parallel": true, "self": 0.0008145660003719968, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017468759997427696, "count": 8, "is_parallel": true, "self": 0.0017468759997427696 } } }, "UnityEnvironment.step": { "total": 0.04628038700002435, "count": 1, "is_parallel": true, "self": 0.0005093489999126177, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045241199995871284, "count": 1, "is_parallel": true, "self": 0.00045241199995871284 }, "communicator.exchange": { "total": 0.0436588219999976, "count": 1, "is_parallel": true, "self": 0.0436588219999976 }, "steps_from_proto": { "total": 0.0016598040001554182, "count": 1, "is_parallel": true, "self": 0.00034120800000891904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013185960001464991, "count": 8, "is_parallel": true, "self": 0.0013185960001464991 } } } } } } }, "UnityEnvironment.step": { "total": 1092.1524054539746, "count": 63437, "is_parallel": true, "self": 30.392961995997666, "children": { "UnityEnvironment._generate_step_input": { "total": 22.418045829942002, "count": 63437, "is_parallel": true, "self": 22.418045829942002 }, "communicator.exchange": { "total": 948.9120338280391, "count": 63437, "is_parallel": true, "self": 948.9120338280391 }, "steps_from_proto": { "total": 90.42936379999583, "count": 63437, "is_parallel": true, "self": 17.60526451485157, "children": { "_process_rank_one_or_two_observation": { "total": 72.82409928514426, "count": 507496, "is_parallel": true, "self": 72.82409928514426 } } } } } } } } } } }, "trainer_advance": { "total": 671.1192872910128, "count": 63438, "self": 2.348435439039804, "children": { "process_trajectory": { "total": 122.03270620797684, "count": 63438, "self": 121.78790839897692, "children": { "RLTrainer._checkpoint": { "total": 0.24479780899991965, "count": 2, "self": 0.24479780899991965 } } }, "_update_policy": { "total": 546.7381456439962, "count": 447, "self": 299.62561800302865, "children": { "TorchPPOOptimizer.update": { "total": 247.11252764096753, "count": 22764, "self": 247.11252764096753 } } } } } } }, "trainer_threads": { "total": 1.1110005289083347e-06, "count": 1, "self": 1.1110005289083347e-06 }, "TrainerController._save_models": { "total": 0.12966653900002711, "count": 1, "self": 0.002103689000250597, "children": { "RLTrainer._checkpoint": { "total": 0.12756284999977652, "count": 1, "self": 0.12756284999977652 } } } } } } }