{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3326510787010193, "min": 0.3230558931827545, "max": 1.4894448518753052, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9798.5703125, "min": 9798.5703125, "max": 45183.80078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989915.0, "min": 29946.0, "max": 989915.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989915.0, "min": 29946.0, "max": 989915.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4596026837825775, "min": -0.1156543418765068, "max": 0.5197778940200806, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 123.17351531982422, "min": -27.757041931152344, "max": 141.3795928955078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0023681391030550003, "min": -0.015618355944752693, "max": 0.3161812126636505, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6346612572669983, "min": -4.24819278717041, "max": 74.93494415283203, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0678751615226805, "min": 0.06474885821047764, "max": 0.07475457629755398, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9502522613175269, "min": 0.5390259911140234, "max": 1.0396951321323, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014891964754191455, "min": 0.00039158475779309547, "max": 0.015148671742367911, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20848750655868037, "min": 0.00430743233572405, "max": 0.21265881514652094, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.732125994085712e-06, "min": 7.732125994085712e-06, "max": 0.000295014226661925, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010824976391719998, "min": 0.00010824976391719998, "max": 0.0033818159727280997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257734285714286, "min": 0.10257734285714286, "max": 0.198338075, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360828, "min": 1.4360828, "max": 2.5273868999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026747655142857137, "min": 0.00026747655142857137, "max": 0.0098339736925, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037446717199999995, "min": 0.0037446717199999995, "max": 0.11275446281000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010532896034419537, "min": 0.010532896034419537, "max": 0.3225255310535431, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14746055006980896, "min": 0.14746055006980896, "max": 2.5802042484283447, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 399.46666666666664, "min": 379.7294117647059, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29960.0, "min": 16873.0, "max": 34673.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4359107913600433, "min": -0.9999375520274043, "max": 1.5302584359279046, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 106.2573985606432, "min": -31.998001664876938, "max": 124.09419818967581, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4359107913600433, "min": -0.9999375520274043, "max": 1.5302584359279046, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 106.2573985606432, "min": -31.998001664876938, "max": 124.09419818967581, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043802913162712565, "min": 0.043461986211782676, "max": 6.801037587663707, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2414155740407296, "min": 3.1300154372875113, "max": 115.61763899028301, "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": "1744418879", "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 Training1 --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": "1744421099" }, "total": 2220.4605057890003, "count": 1, "self": 0.47592336000070645, "children": { "run_training.setup": { "total": 0.02097656299974915, "count": 1, "self": 0.02097656299974915 }, "TrainerController.start_learning": { "total": 2219.963605866, "count": 1, "self": 1.287990899905708, "children": { "TrainerController._reset_env": { "total": 3.024095395000586, "count": 1, "self": 3.024095395000586 }, "TrainerController.advance": { "total": 2215.5654601560946, "count": 63642, "self": 1.358040273923507, "children": { "env_step": { "total": 1533.085865783004, "count": 63642, "self": 1383.526175805001, "children": { "SubprocessEnvManager._take_step": { "total": 148.8237194159101, "count": 63642, "self": 4.505598698050562, "children": { "TorchPolicy.evaluate": { "total": 144.31812071785953, "count": 62565, "self": 144.31812071785953 } } }, "workers": { "total": 0.7359705620929162, "count": 63642, "self": 0.0, "children": { "worker_root": { "total": 2214.9881754300213, "count": 63642, "is_parallel": true, "self": 941.6920669539231, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024133739998433157, "count": 1, "is_parallel": true, "self": 0.0007029499993222998, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017104240005210158, "count": 8, "is_parallel": true, "self": 0.0017104240005210158 } } }, "UnityEnvironment.step": { "total": 0.04965212700062693, "count": 1, "is_parallel": true, "self": 0.0006086140010665986, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005258740002318518, "count": 1, "is_parallel": true, "self": 0.0005258740002318518 }, "communicator.exchange": { "total": 0.04689568499998131, "count": 1, "is_parallel": true, "self": 0.04689568499998131 }, "steps_from_proto": { "total": 0.0016219539993471699, "count": 1, "is_parallel": true, "self": 0.0003639349988588947, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012580190004882752, "count": 8, "is_parallel": true, "self": 0.0012580190004882752 } } } } } } }, "UnityEnvironment.step": { "total": 1273.2961084760982, "count": 63641, "is_parallel": true, "self": 31.6072275801489, "children": { "UnityEnvironment._generate_step_input": { "total": 23.28329508392926, "count": 63641, "is_parallel": true, "self": 23.28329508392926 }, "communicator.exchange": { "total": 1124.1632278851048, "count": 63641, "is_parallel": true, "self": 1124.1632278851048 }, "steps_from_proto": { "total": 94.24235792691525, "count": 63641, "is_parallel": true, "self": 18.58437814986246, "children": { "_process_rank_one_or_two_observation": { "total": 75.65797977705279, "count": 509128, "is_parallel": true, "self": 75.65797977705279 } } } } } } } } } } }, "trainer_advance": { "total": 681.121554099167, "count": 63642, "self": 2.471611600174583, "children": { "process_trajectory": { "total": 126.07052969097822, "count": 63642, "self": 125.80845996497828, "children": { "RLTrainer._checkpoint": { "total": 0.26206972599993605, "count": 2, "self": 0.26206972599993605 } } }, "_update_policy": { "total": 552.5794128080142, "count": 451, "self": 302.45880873806436, "children": { "TorchPPOOptimizer.update": { "total": 250.12060406994988, "count": 22830, "self": 250.12060406994988 } } } } } } }, "trainer_threads": { "total": 9.81999619398266e-07, "count": 1, "self": 9.81999619398266e-07 }, "TrainerController._save_models": { "total": 0.08605843299937987, "count": 1, "self": 0.001498866999099846, "children": { "RLTrainer._checkpoint": { "total": 0.08455956600028003, "count": 1, "self": 0.08455956600028003 } } } } } } }