{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5344816446304321, "min": 0.5014800429344177, "max": 1.3457447290420532, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16128.517578125, "min": 14996.2587890625, "max": 40824.51171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49341973662376404, "min": -0.09664840251207352, "max": 0.49341973662376404, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.19700622558594, "min": -23.195615768432617, "max": 135.19700622558594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008070732466876507, "min": -0.003329928033053875, "max": 0.3889438211917877, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.21138072013855, "min": -0.8890907764434814, "max": 92.1796875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0700330212899384, "min": 0.06376280833085599, "max": 0.0729132254118324, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9804622980591374, "min": 0.5103925778828268, "max": 1.0753410970056017, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017971637357342325, "min": 0.0004313135532457675, "max": 0.017971637357342325, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2516029230027925, "min": 0.0038818219792119074, "max": 0.2516029230027925, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.702404575421426e-06, "min": 7.702404575421426e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010783366405589996, "min": 0.00010783366405589996, "max": 0.0031364756545082, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256743571428573, "min": 0.10256743571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359441000000002, "min": 1.3886848, "max": 2.4429124, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002664868278571428, "min": 0.0002664868278571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003730815589999999, "min": 0.003730815589999999, "max": 0.10457463082, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011575299315154552, "min": 0.011575299315154552, "max": 0.45811840891838074, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16205419600009918, "min": 0.16205419600009918, "max": 3.2068288326263428, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 349.57471264367814, "min": 349.57471264367814, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30413.0, "min": 15984.0, "max": 32522.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5814367622650902, "min": -1.0000000521540642, "max": 1.5814367622650902, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.58499831706285, "min": -31.998801663517952, "max": 137.58499831706285, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5814367622650902, "min": -1.0000000521540642, "max": 1.5814367622650902, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.58499831706285, "min": -31.998801663517952, "max": 137.58499831706285, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04187670622195583, "min": 0.04187670622195583, "max": 8.57827686611563, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.643273441310157, "min": 3.643273441310157, "max": 137.25242985785007, "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": "1702203725", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702206419" }, "total": 2693.5533698159998, "count": 1, "self": 0.527389733999371, "children": { "run_training.setup": { "total": 0.059255661000179316, "count": 1, "self": 0.059255661000179316 }, "TrainerController.start_learning": { "total": 2692.9667244210004, "count": 1, "self": 2.1227193670233646, "children": { "TrainerController._reset_env": { "total": 3.2769526669999323, "count": 1, "self": 3.2769526669999323 }, "TrainerController.advance": { "total": 2687.4701073229767, "count": 63563, "self": 2.2861580978401435, "children": { "env_step": { "total": 1926.21533386208, "count": 63563, "self": 1738.2369490600784, "children": { "SubprocessEnvManager._take_step": { "total": 186.56018001997313, "count": 63563, "self": 6.365758082961747, "children": { "TorchPolicy.evaluate": { "total": 180.19442193701138, "count": 62570, "self": 180.19442193701138 } } }, "workers": { "total": 1.418204782028397, "count": 63563, "self": 0.0, "children": { "worker_root": { "total": 2686.7990328109895, "count": 63563, "is_parallel": true, "self": 1112.97466936904, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002247166000188372, "count": 1, "is_parallel": true, "self": 0.0007018600001629238, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015453060000254482, "count": 8, "is_parallel": true, "self": 0.0015453060000254482 } } }, "UnityEnvironment.step": { "total": 0.05425628600005439, "count": 1, "is_parallel": true, "self": 0.0007421229997817136, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005881660001705313, "count": 1, "is_parallel": true, "self": 0.0005881660001705313 }, "communicator.exchange": { "total": 0.05085121300021456, "count": 1, "is_parallel": true, "self": 0.05085121300021456 }, "steps_from_proto": { "total": 0.002074783999887586, "count": 1, "is_parallel": true, "self": 0.0005049299998063361, "children": { "_process_rank_one_or_two_observation": { "total": 0.00156985400008125, "count": 8, "is_parallel": true, "self": 0.00156985400008125 } } } } } } }, "UnityEnvironment.step": { "total": 1573.8243634419496, "count": 63562, "is_parallel": true, "self": 42.257161281767594, "children": { "UnityEnvironment._generate_step_input": { "total": 29.670986884085096, "count": 63562, "is_parallel": true, "self": 29.670986884085096 }, "communicator.exchange": { "total": 1376.9738406130468, "count": 63562, "is_parallel": true, "self": 1376.9738406130468 }, "steps_from_proto": { "total": 124.92237466305005, "count": 63562, "is_parallel": true, "self": 26.907920463041137, "children": { "_process_rank_one_or_two_observation": { "total": 98.01445420000891, "count": 508496, "is_parallel": true, "self": 98.01445420000891 } } } } } } } } } } }, "trainer_advance": { "total": 758.9686153630566, "count": 63563, "self": 4.244616111019013, "children": { "process_trajectory": { "total": 155.10108178303017, "count": 63563, "self": 154.88973119602997, "children": { "RLTrainer._checkpoint": { "total": 0.21135058700019727, "count": 2, "self": 0.21135058700019727 } } }, "_update_policy": { "total": 599.6229174690075, "count": 440, "self": 363.4779765999863, "children": { "TorchPPOOptimizer.update": { "total": 236.14494086902118, "count": 22818, "self": 236.14494086902118 } } } } } } }, "trainer_threads": { "total": 1.1419997463235632e-06, "count": 1, "self": 1.1419997463235632e-06 }, "TrainerController._save_models": { "total": 0.09694392200071889, "count": 1, "self": 0.0014732670006196713, "children": { "RLTrainer._checkpoint": { "total": 0.09547065500009921, "count": 1, "self": 0.09547065500009921 } } } } } } }