{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4779961407184601, "min": 0.4779961407184601, "max": 1.4685277938842773, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14508.138671875, "min": 14508.138671875, "max": 44549.2578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989944.0, "min": 29998.0, "max": 989944.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989944.0, "min": 29998.0, "max": 989944.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4102116823196411, "min": -0.09211139380931854, "max": 0.42243072390556335, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.29588317871094, "min": -22.106735229492188, "max": 112.78900146484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.044330425560474396, "min": -0.006958050653338432, "max": 0.26223960518836975, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.703232765197754, "min": -1.8230092525482178, "max": 62.41302490234375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.069967219832867, "min": 0.06535719927965795, "max": 0.0722512730733595, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9795410776601379, "min": 0.49665303750785905, "max": 1.0837690961003925, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014003809110026513, "min": 0.0006779805582681545, "max": 0.014003809110026513, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1960533275403712, "min": 0.009491727815754162, "max": 0.1960533275403712, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.621811745142856e-06, "min": 7.621811745142856e-06, "max": 0.00029523643015928573, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010670536443199997, "min": 0.00010670536443199997, "max": 0.0036328798890400997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254057142857144, "min": 0.10254057142857144, "max": 0.19841214285714284, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355680000000002, "min": 1.388885, "max": 2.6109599, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002638030857142857, "min": 0.0002638030857142857, "max": 0.00984137307142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036932431999999998, "min": 0.0036932431999999998, "max": 0.12111489401000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0071409898810088634, "min": 0.006970789283514023, "max": 0.2896631360054016, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09997385740280151, "min": 0.09759104996919632, "max": 2.027642011642456, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 455.2835820895522, "min": 420.32876712328766, "max": 989.2258064516129, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30504.0, "min": 16669.0, "max": 32611.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3954178838809925, "min": -0.9285333854230967, "max": 1.4864322348467764, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.4929982200265, "min": -30.641601718962193, "max": 105.31439827382565, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3954178838809925, "min": -0.9285333854230967, "max": 1.4864322348467764, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.4929982200265, "min": -30.641601718962193, "max": 105.31439827382565, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033630693684081864, "min": 0.030197729715401283, "max": 5.477940076414277, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.253256476833485, "min": 2.1287830342480447, "max": 93.1249812990427, "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": "1713274582", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713276696" }, "total": 2114.550179289, "count": 1, "self": 0.48935057899961976, "children": { "run_training.setup": { "total": 0.05064673400011088, "count": 1, "self": 0.05064673400011088 }, "TrainerController.start_learning": { "total": 2114.0101819760002, "count": 1, "self": 1.4856723380626136, "children": { "TrainerController._reset_env": { "total": 2.2959593489995314, "count": 1, "self": 2.2959593489995314 }, "TrainerController.advance": { "total": 2110.1401115789386, "count": 63513, "self": 1.5168331667346138, "children": { "env_step": { "total": 1463.6947361520988, "count": 63513, "self": 1321.8460662546968, "children": { "SubprocessEnvManager._take_step": { "total": 140.93854921712864, "count": 63513, "self": 4.856412865038692, "children": { "TorchPolicy.evaluate": { "total": 136.08213635208995, "count": 62562, "self": 136.08213635208995 } } }, "workers": { "total": 0.9101206802733941, "count": 63513, "self": 0.0, "children": { "worker_root": { "total": 2108.741862807161, "count": 63513, "is_parallel": true, "self": 912.7085175011916, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002193940000324801, "count": 1, "is_parallel": true, "self": 0.0006487499995273538, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015451900007974473, "count": 8, "is_parallel": true, "self": 0.0015451900007974473 } } }, "UnityEnvironment.step": { "total": 0.048754239000118105, "count": 1, "is_parallel": true, "self": 0.0006324780006252695, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008708389996172627, "count": 1, "is_parallel": true, "self": 0.0008708389996172627 }, "communicator.exchange": { "total": 0.045554616000117676, "count": 1, "is_parallel": true, "self": 0.045554616000117676 }, "steps_from_proto": { "total": 0.0016963059997578966, "count": 1, "is_parallel": true, "self": 0.00033794699811551254, "children": { "_process_rank_one_or_two_observation": { "total": 0.001358359001642384, "count": 8, "is_parallel": true, "self": 0.001358359001642384 } } } } } } }, "UnityEnvironment.step": { "total": 1196.0333453059693, "count": 63512, "is_parallel": true, "self": 35.916302983595415, "children": { "UnityEnvironment._generate_step_input": { "total": 24.465102254996054, "count": 63512, "is_parallel": true, "self": 24.465102254996054 }, "communicator.exchange": { "total": 1033.9667752451442, "count": 63512, "is_parallel": true, "self": 1033.9667752451442 }, "steps_from_proto": { "total": 101.68516482223367, "count": 63512, "is_parallel": true, "self": 21.021399252092124, "children": { "_process_rank_one_or_two_observation": { "total": 80.66376557014155, "count": 508096, "is_parallel": true, "self": 80.66376557014155 } } } } } } } } } } }, "trainer_advance": { "total": 644.9285422601051, "count": 63513, "self": 2.8649157070067304, "children": { "process_trajectory": { "total": 128.76475633009886, "count": 63513, "self": 128.5590487560985, "children": { "RLTrainer._checkpoint": { "total": 0.2057075740003711, "count": 2, "self": 0.2057075740003711 } } }, "_update_policy": { "total": 513.2988702229995, "count": 455, "self": 299.6773016270454, "children": { "TorchPPOOptimizer.update": { "total": 213.62156859595416, "count": 22761, "self": 213.62156859595416 } } } } } } }, "trainer_threads": { "total": 1.0050007404061034e-06, "count": 1, "self": 1.0050007404061034e-06 }, "TrainerController._save_models": { "total": 0.08843770499879611, "count": 1, "self": 0.001518376997410087, "children": { "RLTrainer._checkpoint": { "total": 0.08691932800138602, "count": 1, "self": 0.08691932800138602 } } } } } } }