{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3922267556190491, "min": 0.3866303563117981, "max": 1.399727463722229, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11722.873046875, "min": 11567.98046875, "max": 42462.1328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989934.0, "min": 29892.0, "max": 989934.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989934.0, "min": 29892.0, "max": 989934.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49660590291023254, "min": -0.11000493168830872, "max": 0.5368474125862122, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.04965209960938, "min": -26.511188507080078, "max": 146.55934143066406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0040316455997526646, "min": -0.00504383584484458, "max": 0.38489019870758057, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.1288607120513916, "min": -1.2710466384887695, "max": 91.21897888183594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06758369111394998, "min": 0.06590624569784594, "max": 0.07301912019084697, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9461716755952997, "min": 0.48804675590115776, "max": 1.0774935156394563, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015542732160178102, "min": 0.000428433386609722, "max": 0.015997215332823715, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21759825024249344, "min": 0.0055696340259263856, "max": 0.22396101465953203, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.364090402478571e-06, "min": 7.364090402478571e-06, "max": 0.00029523548730245715, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010309726563469999, "min": 0.00010309726563469999, "max": 0.0035078624307125993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245466428571427, "min": 0.10245466428571427, "max": 0.19841182857142856, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343652999999998, "min": 1.3888828, "max": 2.5692874, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025522096214285715, "min": 0.00025522096214285715, "max": 0.009841341674285714, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00357309347, "min": 0.00357309347, "max": 0.11695181125999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00981693435460329, "min": 0.009750180877745152, "max": 0.45569881796836853, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13743707537651062, "min": 0.13650253415107727, "max": 3.189891815185547, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 366.61176470588236, "min": 365.4457831325301, "max": 993.84375, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31162.0, "min": 16563.0, "max": 34146.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5392352720393854, "min": -0.931050052633509, "max": 1.566283528846276, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.83499812334776, "min": -30.576401762664318, "max": 130.83499812334776, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5392352720393854, "min": -0.931050052633509, "max": 1.566283528846276, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.83499812334776, "min": -30.576401762664318, "max": 130.83499812334776, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03763323975363164, "min": 0.03600312006086145, "max": 8.886781034224173, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1988253790586896, "min": 2.9882589650515, "max": 151.07527758181095, "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": "1733594254", "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": "1733596466" }, "total": 2211.90384996, "count": 1, "self": 0.7673126810000213, "children": { "run_training.setup": { "total": 0.056223680000130116, "count": 1, "self": 0.056223680000130116 }, "TrainerController.start_learning": { "total": 2211.080313599, "count": 1, "self": 1.3059139290407984, "children": { "TrainerController._reset_env": { "total": 2.229277563000096, "count": 1, "self": 2.229277563000096 }, "TrainerController.advance": { "total": 2207.4124035149594, "count": 63751, "self": 1.4212650069553092, "children": { "env_step": { "total": 1523.1148456730336, "count": 63751, "self": 1377.8534226279774, "children": { "SubprocessEnvManager._take_step": { "total": 144.4874977150091, "count": 63751, "self": 4.512598082088289, "children": { "TorchPolicy.evaluate": { "total": 139.97489963292082, "count": 62559, "self": 139.97489963292082 } } }, "workers": { "total": 0.7739253300471773, "count": 63751, "self": 0.0, "children": { "worker_root": { "total": 2206.268048386041, "count": 63751, "is_parallel": true, "self": 940.7973410330319, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020193970001400885, "count": 1, "is_parallel": true, "self": 0.0006225409997568931, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013968560003831954, "count": 8, "is_parallel": true, "self": 0.0013968560003831954 } } }, "UnityEnvironment.step": { "total": 0.04643912699998509, "count": 1, "is_parallel": true, "self": 0.0006761290001122688, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004438519999894197, "count": 1, "is_parallel": true, "self": 0.0004438519999894197 }, "communicator.exchange": { "total": 0.04370923400006177, "count": 1, "is_parallel": true, "self": 0.04370923400006177 }, "steps_from_proto": { "total": 0.0016099119998216338, "count": 1, "is_parallel": true, "self": 0.0003433869999298622, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012665249998917716, "count": 8, "is_parallel": true, "self": 0.0012665249998917716 } } } } } } }, "UnityEnvironment.step": { "total": 1265.470707353009, "count": 63750, "is_parallel": true, "self": 33.05608089100588, "children": { "UnityEnvironment._generate_step_input": { "total": 22.64509350000685, "count": 63750, "is_parallel": true, "self": 22.64509350000685 }, "communicator.exchange": { "total": 1115.1921159449817, "count": 63750, "is_parallel": true, "self": 1115.1921159449817 }, "steps_from_proto": { "total": 94.57741701701457, "count": 63750, "is_parallel": true, "self": 18.65953094308884, "children": { "_process_rank_one_or_two_observation": { "total": 75.91788607392573, "count": 510000, "is_parallel": true, "self": 75.91788607392573 } } } } } } } } } } }, "trainer_advance": { "total": 682.8762928349702, "count": 63751, "self": 2.451957529953688, "children": { "process_trajectory": { "total": 130.91753675902305, "count": 63751, "self": 130.68776227902322, "children": { "RLTrainer._checkpoint": { "total": 0.2297744799998327, "count": 2, "self": 0.2297744799998327 } } }, "_update_policy": { "total": 549.5067985459934, "count": 453, "self": 308.0799111980323, "children": { "TorchPPOOptimizer.update": { "total": 241.42688734796116, "count": 22785, "self": 241.42688734796116 } } } } } } }, "trainer_threads": { "total": 1.1979996088484768e-06, "count": 1, "self": 1.1979996088484768e-06 }, "TrainerController._save_models": { "total": 0.13271739400033766, "count": 1, "self": 0.0014724450002177036, "children": { "RLTrainer._checkpoint": { "total": 0.13124494900011996, "count": 1, "self": 0.13124494900011996 } } } } } } }