{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36168980598449707, "min": 0.332235723733902, "max": 1.3537042140960693, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10781.25, "min": 9866.072265625, "max": 41065.97265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3709689676761627, "min": -0.08730626106262207, "max": 0.3955533504486084, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 98.30677795410156, "min": -20.953502655029297, "max": 106.40385437011719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03553295508027077, "min": 0.0022034409921616316, "max": 0.3950938880443573, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.41623306274414, "min": 0.5486568212509155, "max": 95.2176284790039, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07085979027102614, "min": 0.06470947051927475, "max": 0.07338828907687235, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9920370637943658, "min": 0.5137180235381065, "max": 1.0800788726779749, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013889445968656914, "min": 0.0009313894743617715, "max": 0.014136260964894768, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19445224356119678, "min": 0.012108063166703029, "max": 0.21204391447342152, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.379283254557141e-06, "min": 7.379283254557141e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010330996556379997, "min": 0.00010330996556379997, "max": 0.0036339835886722, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245972857142857, "min": 0.10245972857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344362, "min": 1.3886848, "max": 2.6113278, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025572688428571427, "min": 0.00025572688428571427, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00358017638, "min": 0.00358017638, "max": 0.12115164721999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016356972977519035, "min": 0.016356972977519035, "max": 0.6327592134475708, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2289976328611374, "min": 0.2289976328611374, "max": 4.429314613342285, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 473.1587301587302, "min": 459.8840579710145, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29809.0, "min": 15984.0, "max": 33729.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3045523603047644, "min": -1.0000000521540642, "max": 1.4239133098473151, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 82.18679869920015, "min": -29.23980161547661, "max": 92.26279878616333, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3045523603047644, "min": -1.0000000521540642, "max": 1.4239133098473151, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 82.18679869920015, "min": -29.23980161547661, "max": 92.26279878616333, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08033744213707184, "min": 0.08033744213707184, "max": 12.267523353919387, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.0612588546355255, "min": 5.0612588546355255, "max": 196.2803736627102, "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": "1715773845", "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": "1715777300" }, "total": 3454.290163313, "count": 1, "self": 0.6893238699999529, "children": { "run_training.setup": { "total": 0.06619674100011252, "count": 1, "self": 0.06619674100011252 }, "TrainerController.start_learning": { "total": 3453.534642702, "count": 1, "self": 2.6274057308264673, "children": { "TrainerController._reset_env": { "total": 2.9811125359997277, "count": 1, "self": 2.9811125359997277 }, "TrainerController.advance": { "total": 3447.8184494131747, "count": 63537, "self": 2.9185468542705166, "children": { "env_step": { "total": 2295.2558236209798, "count": 63537, "self": 2114.3017874949896, "children": { "SubprocessEnvManager._take_step": { "total": 179.26950235089816, "count": 63537, "self": 8.102439216821494, "children": { "TorchPolicy.evaluate": { "total": 171.16706313407667, "count": 62566, "self": 171.16706313407667 } } }, "workers": { "total": 1.6845337750919498, "count": 63537, "self": 0.0, "children": { "worker_root": { "total": 3445.579147448971, "count": 63537, "is_parallel": true, "self": 1546.2820195639306, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035194830002183153, "count": 1, "is_parallel": true, "self": 0.0011272279998593149, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023922550003590004, "count": 8, "is_parallel": true, "self": 0.0023922550003590004 } } }, "UnityEnvironment.step": { "total": 0.14050427100028173, "count": 1, "is_parallel": true, "self": 0.0008534260000487848, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008023230002436321, "count": 1, "is_parallel": true, "self": 0.0008023230002436321 }, "communicator.exchange": { "total": 0.13675644499971895, "count": 1, "is_parallel": true, "self": 0.13675644499971895 }, "steps_from_proto": { "total": 0.002092077000270365, "count": 1, "is_parallel": true, "self": 0.0004561310001918173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016359460000785475, "count": 8, "is_parallel": true, "self": 0.0016359460000785475 } } } } } } }, "UnityEnvironment.step": { "total": 1899.2971278850405, "count": 63536, "is_parallel": true, "self": 55.86770819687035, "children": { "UnityEnvironment._generate_step_input": { "total": 33.13581512909968, "count": 63536, "is_parallel": true, "self": 33.13581512909968 }, "communicator.exchange": { "total": 1673.8121784120885, "count": 63536, "is_parallel": true, "self": 1673.8121784120885 }, "steps_from_proto": { "total": 136.4814261469819, "count": 63536, "is_parallel": true, "self": 30.82965453187444, "children": { "_process_rank_one_or_two_observation": { "total": 105.65177161510746, "count": 508288, "is_parallel": true, "self": 105.65177161510746 } } } } } } } } } } }, "trainer_advance": { "total": 1149.6440789379244, "count": 63537, "self": 5.521701177053728, "children": { "process_trajectory": { "total": 183.8459870478746, "count": 63537, "self": 183.6289911318745, "children": { "RLTrainer._checkpoint": { "total": 0.21699591600008716, "count": 2, "self": 0.21699591600008716 } } }, "_update_policy": { "total": 960.2763907129961, "count": 456, "self": 384.4068423490271, "children": { "TorchPPOOptimizer.update": { "total": 575.869548363969, "count": 22791, "self": 575.869548363969 } } } } } } }, "trainer_threads": { "total": 1.710999640636146e-06, "count": 1, "self": 1.710999640636146e-06 }, "TrainerController._save_models": { "total": 0.10767331099941657, "count": 1, "self": 0.0025537079991408973, "children": { "RLTrainer._checkpoint": { "total": 0.10511960300027567, "count": 1, "self": 0.10511960300027567 } } } } } } }