{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36235687136650085, "min": 0.35631152987480164, "max": 1.4948190450668335, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10922.8857421875, "min": 10683.64453125, "max": 45346.83203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989966.0, "min": 29947.0, "max": 989966.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989966.0, "min": 29947.0, "max": 989966.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5616320371627808, "min": -0.13826364278793335, "max": 0.6391779184341431, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 157.818603515625, "min": -32.76848220825195, "max": 182.16571044921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01101516280323267, "min": 0.01101516280323267, "max": 0.25807449221611023, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.0952606201171875, "min": 3.0952606201171875, "max": 61.163658142089844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06707372854644846, "min": 0.065976815419789, "max": 0.0742242843922259, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0061059281967268, "min": 0.5022555218250813, "max": 1.0497116708526544, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01554408024660208, "min": 0.0006501302601986454, "max": 0.016415322534157895, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2331612036990312, "min": 0.008451693382582389, "max": 0.2331612036990312, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.436537521186663e-06, "min": 7.436537521186663e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011154806281779995, "min": 0.00011154806281779995, "max": 0.0036327637890788, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247881333333332, "min": 0.10247881333333332, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371821999999997, "min": 1.3886848, "max": 2.6177964, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025763345199999993, "min": 0.00025763345199999993, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003864501779999999, "min": 0.003864501779999999, "max": 0.12111102788000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007234602700918913, "min": 0.007106174249202013, "max": 0.3644375801086426, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1085190400481224, "min": 0.09948644042015076, "max": 2.551063060760498, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 324.98936170212767, "min": 304.4257425742574, "max": 996.1935483870968, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30549.0, "min": 16874.0, "max": 32494.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6537276431918144, "min": -0.9326387626990196, "max": 1.655960380145819, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 155.45039846003056, "min": -29.670601680874825, "max": 167.2519983947277, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6537276431918144, "min": -0.9326387626990196, "max": 1.655960380145819, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 155.45039846003056, "min": -29.670601680874825, "max": 167.2519983947277, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024386967147794612, "min": 0.022095563617191453, "max": 7.007981215329731, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2923749118926935, "min": 2.210133002954535, "max": 119.13568066060543, "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": "1739270980", "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 Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739273194" }, "total": 2214.3934046779996, "count": 1, "self": 0.47616168400008974, "children": { "run_training.setup": { "total": 0.021082431999730034, "count": 1, "self": 0.021082431999730034 }, "TrainerController.start_learning": { "total": 2213.8961605619997, "count": 1, "self": 1.2138471219145686, "children": { "TrainerController._reset_env": { "total": 2.1976176560001477, "count": 1, "self": 2.1976176560001477 }, "TrainerController.advance": { "total": 2210.3985022490847, "count": 63964, "self": 1.2544991041768299, "children": { "env_step": { "total": 1537.224507985994, "count": 63964, "self": 1391.479339359019, "children": { "SubprocessEnvManager._take_step": { "total": 145.0377874419587, "count": 63964, "self": 4.426751380886344, "children": { "TorchPolicy.evaluate": { "total": 140.61103606107235, "count": 62563, "self": 140.61103606107235 } } }, "workers": { "total": 0.707381185016402, "count": 63964, "self": 0.0, "children": { "worker_root": { "total": 2209.1089253899722, "count": 63964, "is_parallel": true, "self": 922.542579755021, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002029481000136002, "count": 1, "is_parallel": true, "self": 0.0006356750004670175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013938059996689844, "count": 8, "is_parallel": true, "self": 0.0013938059996689844 } } }, "UnityEnvironment.step": { "total": 0.046804848999727255, "count": 1, "is_parallel": true, "self": 0.0005130099998496007, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004716369999187009, "count": 1, "is_parallel": true, "self": 0.0004716369999187009 }, "communicator.exchange": { "total": 0.04422527799988529, "count": 1, "is_parallel": true, "self": 0.04422527799988529 }, "steps_from_proto": { "total": 0.0015949240000736609, "count": 1, "is_parallel": true, "self": 0.00034840899979826645, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012465150002753944, "count": 8, "is_parallel": true, "self": 0.0012465150002753944 } } } } } } }, "UnityEnvironment.step": { "total": 1286.5663456349512, "count": 63963, "is_parallel": true, "self": 30.361669990835708, "children": { "UnityEnvironment._generate_step_input": { "total": 22.522444075060776, "count": 63963, "is_parallel": true, "self": 22.522444075060776 }, "communicator.exchange": { "total": 1141.6615908060407, "count": 63963, "is_parallel": true, "self": 1141.6615908060407 }, "steps_from_proto": { "total": 92.02064076301394, "count": 63963, "is_parallel": true, "self": 17.76106641789056, "children": { "_process_rank_one_or_two_observation": { "total": 74.25957434512338, "count": 511704, "is_parallel": true, "self": 74.25957434512338 } } } } } } } } } } }, "trainer_advance": { "total": 671.9194951589138, "count": 63964, "self": 2.406394245964748, "children": { "process_trajectory": { "total": 125.2764621639617, "count": 63964, "self": 125.01677488096175, "children": { "RLTrainer._checkpoint": { "total": 0.25968728299994837, "count": 2, "self": 0.25968728299994837 } } }, "_update_policy": { "total": 544.2366387489874, "count": 458, "self": 300.71979051991866, "children": { "TorchPPOOptimizer.update": { "total": 243.51684822906873, "count": 22788, "self": 243.51684822906873 } } } } } } }, "trainer_threads": { "total": 8.240003808168694e-07, "count": 1, "self": 8.240003808168694e-07 }, "TrainerController._save_models": { "total": 0.08619271099996695, "count": 1, "self": 0.0012697940001089592, "children": { "RLTrainer._checkpoint": { "total": 0.08492291699985799, "count": 1, "self": 0.08492291699985799 } } } } } } }