{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.08631689846515656, "min": 0.0843723863363266, "max": 1.3741669654846191, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 2585.36376953125, "min": 2527.121826171875, "max": 41686.73046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989895.0, "min": 29910.0, "max": 989895.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989895.0, "min": 29910.0, "max": 989895.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09077170491218567, "min": -0.10533519834280014, "max": -0.00047584527055732906, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.78520965576172, "min": -25.280447006225586, "max": -0.11277532577514648, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.6536656618118286, "min": 0.49741488695144653, "max": 0.6628867983818054, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 156.8797607421875, "min": 117.8873291015625, "max": 159.09283447265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06704746414256721, "min": 0.06651772349153243, "max": 0.0749196238989595, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.938664497995941, "min": 0.5244373672927165, "max": 0.9913632133497537, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0013481241059302759, "min": 0.00025611136050515817, "max": 0.008759250811447695, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.018873737483023862, "min": 0.003585559047072214, "max": 0.061314755680133864, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.76000455622143e-06, "min": 7.76000455622143e-06, "max": 0.0002952347158741428, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010864006378710001, "min": 0.00010864006378710001, "max": 0.0034931026356324994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258663571428571, "min": 0.10258663571428571, "max": 0.19841157142857144, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362129, "min": 1.388881, "max": 2.4643675000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026840490785714295, "min": 0.00026840490785714295, "max": 0.009841315985714286, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003757668710000001, "min": 0.003757668710000001, "max": 0.11645031324999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.6511731147766113, "min": 0.5017501711845398, "max": 0.656827449798584, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 9.116423606872559, "min": 3.8151755332946777, "max": 9.195584297180176, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 969.71875, "min": 912.9411764705883, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31031.0, "min": 16581.0, "max": 32557.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8453187975101173, "min": -0.9999125520698726, "max": -0.6339486181735993, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -27.050201520323753, "min": -31.997201666235924, "max": -14.597000896930695, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8453187975101173, "min": -0.9999125520698726, "max": -0.6339486181735993, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -27.050201520323753, "min": -31.997201666235924, "max": -14.597000896930695, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 6.335959123447537, "min": 4.762054389452233, "max": 8.928904919063344, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 202.7506919503212, "min": 124.4823949933052, "max": 207.30974233150482, "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": "1738945684", "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": "1738948242" }, "total": 2558.2735613310006, "count": 1, "self": 0.6443359860004421, "children": { "run_training.setup": { "total": 0.032106014999953914, "count": 1, "self": 0.032106014999953914 }, "TrainerController.start_learning": { "total": 2557.59711933, "count": 1, "self": 2.29046529797688, "children": { "TrainerController._reset_env": { "total": 2.8654860930000723, "count": 1, "self": 2.8654860930000723 }, "TrainerController.advance": { "total": 2552.3434062580236, "count": 62919, "self": 2.2648396070062518, "children": { "env_step": { "total": 1532.3922718760032, "count": 62919, "self": 1376.8568209279429, "children": { "SubprocessEnvManager._take_step": { "total": 154.2586397999985, "count": 62919, "self": 6.612095845212934, "children": { "TorchPolicy.evaluate": { "total": 147.64654395478556, "count": 62558, "self": 147.64654395478556 } } }, "workers": { "total": 1.2768111480618245, "count": 62919, "self": 0.0, "children": { "worker_root": { "total": 2551.149525607083, "count": 62919, "is_parallel": true, "self": 1334.2293891610652, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033978820001721033, "count": 1, "is_parallel": true, "self": 0.0011836109997602762, "children": { "_process_rank_one_or_two_observation": { "total": 0.002214271000411827, "count": 8, "is_parallel": true, "self": 0.002214271000411827 } } }, "UnityEnvironment.step": { "total": 0.06404912799916929, "count": 1, "is_parallel": true, "self": 0.0007139229983295081, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005307410001478274, "count": 1, "is_parallel": true, "self": 0.0005307410001478274 }, "communicator.exchange": { "total": 0.06079819100068562, "count": 1, "is_parallel": true, "self": 0.06079819100068562 }, "steps_from_proto": { "total": 0.002006273000006331, "count": 1, "is_parallel": true, "self": 0.00041423899983783485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015920340001684963, "count": 8, "is_parallel": true, "self": 0.0015920340001684963 } } } } } } }, "UnityEnvironment.step": { "total": 1216.9201364460178, "count": 62918, "is_parallel": true, "self": 41.62290813011441, "children": { "UnityEnvironment._generate_step_input": { "total": 29.57761404307348, "count": 62918, "is_parallel": true, "self": 29.57761404307348 }, "communicator.exchange": { "total": 1026.6266863728133, "count": 62918, "is_parallel": true, "self": 1026.6266863728133 }, "steps_from_proto": { "total": 119.09292790001655, "count": 62918, "is_parallel": true, "self": 25.59458359830205, "children": { "_process_rank_one_or_two_observation": { "total": 93.4983443017145, "count": 503344, "is_parallel": true, "self": 93.4983443017145 } } } } } } } } } } }, "trainer_advance": { "total": 1017.6862947750142, "count": 62919, "self": 4.081787490072202, "children": { "process_trajectory": { "total": 152.19132513693694, "count": 62919, "self": 151.91144841093683, "children": { "RLTrainer._checkpoint": { "total": 0.2798767260001114, "count": 2, "self": 0.2798767260001114 } } }, "_update_policy": { "total": 861.413182148005, "count": 444, "self": 354.2487153989732, "children": { "TorchPPOOptimizer.update": { "total": 507.1644667490318, "count": 22776, "self": 507.1644667490318 } } } } } } }, "trainer_threads": { "total": 1.1379997886251658e-06, "count": 1, "self": 1.1379997886251658e-06 }, "TrainerController._save_models": { "total": 0.09776054299982206, "count": 1, "self": 0.0045322569994823425, "children": { "RLTrainer._checkpoint": { "total": 0.09322828600033972, "count": 1, "self": 0.09322828600033972 } } } } } } }