{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6296213865280151, "min": 0.6296213865280151, "max": 1.346882939338684, "count": 14 }, "Pyramids.Policy.Entropy.sum": { "value": 31360.181640625, "min": 31360.181640625, "max": 69283.65625, "count": 14 }, "Pyramids.Step.mean": { "value": 699962.0, "min": 49967.0, "max": 699962.0, "count": 14 }, "Pyramids.Step.sum": { "value": 699962.0, "min": 49967.0, "max": 699962.0, "count": 14 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.034950681030750275, "min": -0.17846862971782684, "max": -0.034950681030750275, "count": 14 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -14.189976692199707, "min": -71.387451171875, "max": -14.189976692199707, "count": 14 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.057672228664159775, "min": 0.05636841803789139, "max": 0.8730177879333496, "count": 14 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 23.41492462158203, "min": 22.603734970092773, "max": 349.2071228027344, "count": 14 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06808103200379573, "min": 0.0660548517258182, "max": 0.07066063320739396, "count": 14 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.6339447680910975, "min": 1.1228356936588644, "max": 1.657185271470119, "count": 14 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.002755235105143147, "min": 0.0006105524444866818, "max": 0.024435262344709236, "count": 14 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.06612564252343553, "min": 0.013674775818206971, "max": 0.3909641975153478, "count": 14 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.0570346476583334e-05, "min": 1.0570346476583334e-05, "max": 0.00028776094157968745, "count": 14 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000253688315438, "min": 0.000253688315438, "max": 0.00517195023315957, "count": 14 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10458044166666668, "min": 0.10458044166666668, "max": 0.22469640625, "count": 14 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.5099306, "min": 2.5099306, "max": 4.3456735857142865, "count": 14 }, "Pyramids.Policy.Beta.mean": { "value": 0.000361989325, "min": 0.000361989325, "max": 0.00959243921875, "count": 14 }, "Pyramids.Policy.Beta.sum": { "value": 0.0086877438, "min": 0.0086877438, "max": 0.17243593024285717, "count": 14 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016364308074116707, "min": 0.016186978667974472, "max": 0.22421911358833313, "count": 14 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.39274340867996216, "min": 0.37230050563812256, "max": 3.58750581741333, "count": 14 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 917.5370370370371, "min": 910.5849056603773, "max": 984.9583333333334, "count": 14 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 49547.0, "min": 46975.0, "max": 53021.0, "count": 14 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.43656671405942354, "min": -0.9024417178394893, "max": -0.43656671405942354, "count": 14 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -23.57460255920887, "min": -43.31720245629549, "max": -23.57460255920887, "count": 14 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.30559648890738134, "min": -0.6317089721560478, "max": -0.30559648890738134, "count": 14 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.502210400998592, "min": -30.322030663490295, "max": -16.502210400998592, "count": 14 }, "Pyramids.Policy.RndReward.mean": { "value": 0.2361614646732859, "min": 0.23410373455229797, "max": 6.138572417354832, "count": 14 }, "Pyramids.Policy.RndReward.sum": { "value": 12.752719092357438, "min": 12.407497931271791, "max": 294.65147603303194, "count": 14 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724856074", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=PyramidsTraining --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724858387" }, "total": 2312.4001311089996, "count": 1, "self": 0.635490383999695, "children": { "run_training.setup": { "total": 0.07729710600006001, "count": 1, "self": 0.07729710600006001 }, "TrainerController.start_learning": { "total": 2311.687343619, "count": 1, "self": 1.7303244498966706, "children": { "TrainerController._reset_env": { "total": 2.4490010939998683, "count": 1, "self": 2.4490010939998683 }, "TrainerController.advance": { "total": 2307.416328656102, "count": 44197, "self": 1.8102684532759667, "children": { "env_step": { "total": 1470.4861681338812, "count": 44197, "self": 1346.545282081839, "children": { "SubprocessEnvManager._take_step": { "total": 122.9018366780424, "count": 44197, "self": 5.397717925077359, "children": { "TorchPolicy.evaluate": { "total": 117.50411875296504, "count": 43806, "self": 117.50411875296504 } } }, "workers": { "total": 1.03904937399966, "count": 44197, "self": 0.0, "children": { "worker_root": { "total": 2306.437475526901, "count": 44197, "is_parallel": true, "self": 1097.8021753289918, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0037084040000081586, "count": 1, "is_parallel": true, "self": 0.0012668180002037843, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024415859998043743, "count": 8, "is_parallel": true, "self": 0.0024415859998043743 } } }, "UnityEnvironment.step": { "total": 0.07046298799969009, "count": 1, "is_parallel": true, "self": 0.0008658749993628589, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005304960000103165, "count": 1, "is_parallel": true, "self": 0.0005304960000103165 }, "communicator.exchange": { "total": 0.06597360300020227, "count": 1, "is_parallel": true, "self": 0.06597360300020227 }, "steps_from_proto": { "total": 0.0030930140001146356, "count": 1, "is_parallel": true, "self": 0.0007093239992173039, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023836900008973316, "count": 8, "is_parallel": true, "self": 0.0023836900008973316 } } } } } } }, "UnityEnvironment.step": { "total": 1208.6353001979091, "count": 44196, "is_parallel": true, "self": 37.14408519279823, "children": { "UnityEnvironment._generate_step_input": { "total": 22.253714285097885, "count": 44196, "is_parallel": true, "self": 22.253714285097885 }, "communicator.exchange": { "total": 1055.6875865669736, "count": 44196, "is_parallel": true, "self": 1055.6875865669736 }, "steps_from_proto": { "total": 93.54991415303948, "count": 44196, "is_parallel": true, "self": 20.33801209272451, "children": { "_process_rank_one_or_two_observation": { "total": 73.21190206031497, "count": 353568, "is_parallel": true, "self": 73.21190206031497 } } } } } } } } } } }, "trainer_advance": { "total": 835.1198920689449, "count": 44197, "self": 3.3658835199780697, "children": { "process_trajectory": { "total": 123.02462991096672, "count": 44197, "self": 122.86112455996681, "children": { "RLTrainer._checkpoint": { "total": 0.16350535099991248, "count": 1, "self": 0.16350535099991248 } } }, "_update_policy": { "total": 708.7293786380001, "count": 312, "self": 283.15266778598425, "children": { "TorchPPOOptimizer.update": { "total": 425.5767108520158, "count": 15996, "self": 425.5767108520158 } } } } } } }, "trainer_threads": { "total": 1.3450007827486843e-06, "count": 1, "self": 1.3450007827486843e-06 }, "TrainerController._save_models": { "total": 0.09168807400055812, "count": 1, "self": 0.0027633730005618418, "children": { "RLTrainer._checkpoint": { "total": 0.08892470099999628, "count": 1, "self": 0.08892470099999628 } } } } } } }