{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4814678132534027, "min": 0.4814678132534027, "max": 1.4757566452026367, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14544.1796875, "min": 14535.201171875, "max": 44768.5546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29877.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29877.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4016495943069458, "min": -0.09800539165735245, "max": 0.45544177293777466, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 108.44538879394531, "min": -23.717304229736328, "max": 121.60295104980469, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016832606866955757, "min": -0.06303635239601135, "max": 0.22253024578094482, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.544803619384766, "min": -16.011234283447266, "max": 53.852317810058594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0691474534920417, "min": 0.06603029874815078, "max": 0.07305688811150331, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0372118023806254, "min": 0.582033922196243, "max": 1.0958533216725497, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012539857543500451, "min": 0.000873317718231119, "max": 0.014219420939168361, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18809786315250676, "min": 0.012226448055235666, "max": 0.19907189314835705, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.449837516753334e-06, "min": 7.449837516753334e-06, "max": 0.00029500485166505, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001117475627513, "min": 0.0001117475627513, "max": 0.003758442747185799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248324666666667, "min": 0.10248324666666667, "max": 0.19833494999999995, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372487, "min": 1.4775653, "max": 2.6528141999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025807634200000003, "min": 0.00025807634200000003, "max": 0.009833661505, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038711451300000002, "min": 0.0038711451300000002, "max": 0.12529613858, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005538344383239746, "min": 0.005341253709048033, "max": 0.2800745368003845, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08307516574859619, "min": 0.07477755099534988, "max": 2.240596294403076, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.8285714285714, "min": 404.8285714285714, "max": 998.15625, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28338.0, "min": 16164.0, "max": 32742.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4247267423591143, "min": -0.9364250514190644, "max": 1.4247267423591143, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 101.15559870749712, "min": -29.96560164541006, "max": 101.15559870749712, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4247267423591143, "min": -0.9364250514190644, "max": 1.4247267423591143, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 101.15559870749712, "min": -29.96560164541006, "max": 101.15559870749712, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.023616251905455292, "min": 0.023616251905455292, "max": 5.296832508024047, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6767538852873258, "min": 1.6767538852873258, "max": 90.0461526364088, "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": "1739184020", "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": "1739186222" }, "total": 2201.792049945, "count": 1, "self": 0.48743215300055454, "children": { "run_training.setup": { "total": 0.02108578899992608, "count": 1, "self": 0.02108578899992608 }, "TrainerController.start_learning": { "total": 2201.283532003, "count": 1, "self": 1.4439467599950149, "children": { "TrainerController._reset_env": { "total": 2.1165852449998965, "count": 1, "self": 2.1165852449998965 }, "TrainerController.advance": { "total": 2197.6367989890055, "count": 63628, "self": 1.4420454469159267, "children": { "env_step": { "total": 1503.4316107250752, "count": 63628, "self": 1341.8060046550115, "children": { "SubprocessEnvManager._take_step": { "total": 160.79653164706156, "count": 63628, "self": 4.825377938144811, "children": { "TorchPolicy.evaluate": { "total": 155.97115370891675, "count": 62569, "self": 155.97115370891675 } } }, "workers": { "total": 0.8290744230021119, "count": 63628, "self": 0.0, "children": { "worker_root": { "total": 2196.0852346659703, "count": 63628, "is_parallel": true, "self": 972.5755670519841, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020212090000768512, "count": 1, "is_parallel": true, "self": 0.0006434360004732298, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013777729996036214, "count": 8, "is_parallel": true, "self": 0.0013777729996036214 } } }, "UnityEnvironment.step": { "total": 0.049589081000021906, "count": 1, "is_parallel": true, "self": 0.0005719190000945673, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046004399996490974, "count": 1, "is_parallel": true, "self": 0.00046004399996490974 }, "communicator.exchange": { "total": 0.04684542299992245, "count": 1, "is_parallel": true, "self": 0.04684542299992245 }, "steps_from_proto": { "total": 0.001711695000039981, "count": 1, "is_parallel": true, "self": 0.00035319100038577744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013585039996542037, "count": 8, "is_parallel": true, "self": 0.0013585039996542037 } } } } } } }, "UnityEnvironment.step": { "total": 1223.5096676139863, "count": 63627, "is_parallel": true, "self": 32.050181592014496, "children": { "UnityEnvironment._generate_step_input": { "total": 23.796937146007167, "count": 63627, "is_parallel": true, "self": 23.796937146007167 }, "communicator.exchange": { "total": 1068.842170234992, "count": 63627, "is_parallel": true, "self": 1068.842170234992 }, "steps_from_proto": { "total": 98.82037864097265, "count": 63627, "is_parallel": true, "self": 19.813846435023834, "children": { "_process_rank_one_or_two_observation": { "total": 79.00653220594882, "count": 509016, "is_parallel": true, "self": 79.00653220594882 } } } } } } } } } } }, "trainer_advance": { "total": 692.7631428170143, "count": 63628, "self": 2.813987870056735, "children": { "process_trajectory": { "total": 132.4805058139516, "count": 63628, "self": 132.26886879195104, "children": { "RLTrainer._checkpoint": { "total": 0.21163702200055923, "count": 2, "self": 0.21163702200055923 } } }, "_update_policy": { "total": 557.468649133006, "count": 457, "self": 308.3323676199698, "children": { "TorchPPOOptimizer.update": { "total": 249.13628151303624, "count": 22746, "self": 249.13628151303624 } } } } } } }, "trainer_threads": { "total": 8.369997885893099e-07, "count": 1, "self": 8.369997885893099e-07 }, "TrainerController._save_models": { "total": 0.08620017199973518, "count": 1, "self": 0.0013787209995825833, "children": { "RLTrainer._checkpoint": { "total": 0.08482145100015259, "count": 1, "self": 0.08482145100015259 } } } } } } }