{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9589043855667114, "min": 0.9589043855667114, "max": 1.513645887374878, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 29104.666015625, "min": 28856.26953125, "max": 45917.9609375, "count": 10 }, "Pyramids.Step.mean": { "value": 299979.0, "min": 29952.0, "max": 299979.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299979.0, "min": 29952.0, "max": 299979.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09022675454616547, "min": -0.1564602553844452, "max": -0.08755934983491898, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.744647979736328, "min": -37.08108139038086, "max": -20.926685333251953, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027764836326241493, "min": 0.027764836326241493, "max": 0.37460023164749146, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.691325664520264, "min": 6.691325664520264, "max": 88.78025817871094, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06499416559321283, "min": 0.06499416559321283, "max": 0.07280821959798703, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8449241527117669, "min": 0.4707156064150381, "max": 0.8924464246347864, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0011847626953423401, "min": 0.00014726862626475036, "max": 0.006475154046430632, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.015401915039450422, "min": 0.0014726862626475035, "max": 0.045326078325014424, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5110325732487183e-05, "min": 1.5110325732487183e-05, "max": 0.0002838354339596191, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00019643423452233338, "min": 0.00019643423452233338, "max": 0.0019868480377173334, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1050367435897436, "min": 0.1050367435897436, "max": 0.19461180952380958, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3654776666666668, "min": 1.2970453333333334, "max": 1.6225166666666668, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005131706846153847, "min": 0.0005131706846153847, "max": 0.00946171977142857, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.006671218900000002, "min": 0.006671218900000002, "max": 0.0662320384, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02476278692483902, "min": 0.02476278692483902, "max": 0.3617054522037506, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.32191622257232666, "min": 0.32191622257232666, "max": 2.531938076019287, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 989.65625, "min": 961.1428571428571, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31669.0, "min": 15984.0, "max": 32306.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8654188006184995, "min": -1.0000000521540642, "max": -0.7713143350113005, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -27.693401619791985, "min": -32.000001668930054, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8654188006184995, "min": -1.0000000521540642, "max": -0.7713143350113005, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -27.693401619791985, "min": -32.000001668930054, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.25636011888855137, "min": 0.25636011888855137, "max": 7.56410160753876, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 8.203523804433644, "min": 6.036228194832802, "max": 121.02562572062016, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1730360579", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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 Training2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730361526" }, "total": 947.2282882859997, "count": 1, "self": 0.8693299529995784, "children": { "run_training.setup": { "total": 0.1471173990000807, "count": 1, "self": 0.1471173990000807 }, "TrainerController.start_learning": { "total": 946.2118409340001, "count": 1, "self": 0.7711936619718927, "children": { "TrainerController._reset_env": { "total": 3.622319268999945, "count": 1, "self": 3.622319268999945 }, "TrainerController.advance": { "total": 941.4704108670282, "count": 18843, "self": 0.8351083480547459, "children": { "env_step": { "total": 585.9778438649901, "count": 18843, "self": 533.0709080600025, "children": { "SubprocessEnvManager._take_step": { "total": 52.46406897798147, "count": 18843, "self": 2.4254843579535645, "children": { "TorchPolicy.evaluate": { "total": 50.038584620027905, "count": 18793, "self": 50.038584620027905 } } }, "workers": { "total": 0.442866827006128, "count": 18843, "self": 0.0, "children": { "worker_root": { "total": 943.8359750790173, "count": 18843, "is_parallel": true, "self": 467.7607422090184, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0038299130001178128, "count": 1, "is_parallel": true, "self": 0.0012187310007902852, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026111819993275276, "count": 8, "is_parallel": true, "self": 0.0026111819993275276 } } }, "UnityEnvironment.step": { "total": 0.09008614399999715, "count": 1, "is_parallel": true, "self": 0.0009192699997129239, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005570000000716391, "count": 1, "is_parallel": true, "self": 0.0005570000000716391 }, "communicator.exchange": { "total": 0.08611011000016333, "count": 1, "is_parallel": true, "self": 0.08611011000016333 }, "steps_from_proto": { "total": 0.002499764000049254, "count": 1, "is_parallel": true, "self": 0.0004863589997512463, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020134050002980075, "count": 8, "is_parallel": true, "self": 0.0020134050002980075 } } } } } } }, "UnityEnvironment.step": { "total": 476.0752328699989, "count": 18842, "is_parallel": true, "self": 16.068795364004018, "children": { "UnityEnvironment._generate_step_input": { "total": 9.667163473999153, "count": 18842, "is_parallel": true, "self": 9.667163473999153 }, "communicator.exchange": { "total": 410.0834774200114, "count": 18842, "is_parallel": true, "self": 410.0834774200114 }, "steps_from_proto": { "total": 40.25579661198435, "count": 18842, "is_parallel": true, "self": 8.836506880904835, "children": { "_process_rank_one_or_two_observation": { "total": 31.419289731079516, "count": 150736, "is_parallel": true, "self": 31.419289731079516 } } } } } } } } } } }, "trainer_advance": { "total": 354.65745865398344, "count": 18843, "self": 1.0641512489710294, "children": { "process_trajectory": { "total": 55.32828550201293, "count": 18843, "self": 55.32828550201293 }, "_update_policy": { "total": 298.2650219029995, "count": 102, "self": 118.41903720799928, "children": { "TorchPPOOptimizer.update": { "total": 179.8459846950002, "count": 6903, "self": 179.8459846950002 } } } } } } }, "trainer_threads": { "total": 1.5370001165138092e-06, "count": 1, "self": 1.5370001165138092e-06 }, "TrainerController._save_models": { "total": 0.3479155989998617, "count": 1, "self": 0.0038136989996928605, "children": { "RLTrainer._checkpoint": { "total": 0.3441019000001688, "count": 1, "self": 0.3441019000001688 } } } } } } }