{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4460318386554718, "min": 0.44211599230766296, "max": 1.4537209272384644, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13252.498046875, "min": 13252.498046875, "max": 44100.078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5842247009277344, "min": -0.08802789449691772, "max": 0.5842247009277344, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.75137329101562, "min": -21.2147216796875, "max": 164.75137329101562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.3349430561065674, "min": -0.0015548632945865393, "max": 1.3349430561065674, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 376.4539489746094, "min": -0.42603254318237305, "max": 376.4539489746094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07265878431748465, "min": 0.06419499818740591, "max": 0.07265878431748465, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0172229804447852, "min": 0.4893843500375488, "max": 1.067990642523749, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.1155083061062864, "min": 9.186684581824325e-05, "max": 0.1155083061062864, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.6171162854880097, "min": 0.0011942689956371622, "max": 1.6171162854880097, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.693511721242856e-06, "min": 7.693511721242856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010770916409739998, "min": 0.00010770916409739998, "max": 0.0032552750149084002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256447142857143, "min": 0.10256447142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359026000000001, "min": 1.3691136000000002, "max": 2.4017749, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002661906957142857, "min": 0.0002661906957142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00372666974, "min": 0.00372666974, "max": 0.10853065083999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008882294408977032, "min": 0.008882294408977032, "max": 0.350123792886734, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1243521198630333, "min": 0.1243521198630333, "max": 2.450866460800171, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 336.20212765957444, "min": 336.20212765957444, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31603.0, "min": 15984.0, "max": 33583.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.578670191320967, "min": -1.0000000521540642, "max": 1.578670191320967, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.3949979841709, "min": -32.000001668930054, "max": 148.3949979841709, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.578670191320967, "min": -1.0000000521540642, "max": 1.578670191320967, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.3949979841709, "min": -32.000001668930054, "max": 148.3949979841709, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030779373164206963, "min": 0.030779373164206963, "max": 6.856070193462074, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8932610774354544, "min": 2.661539213040669, "max": 109.69712309539318, "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": "1744015930", "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": "1744018221" }, "total": 2290.722073011, "count": 1, "self": 0.43676146599955246, "children": { "run_training.setup": { "total": 0.02109555900005944, "count": 1, "self": 0.02109555900005944 }, "TrainerController.start_learning": { "total": 2290.264215986, "count": 1, "self": 1.573788936006622, "children": { "TrainerController._reset_env": { "total": 2.2342461240000375, "count": 1, "self": 2.2342461240000375 }, "TrainerController.advance": { "total": 2286.3607311059936, "count": 63647, "self": 1.6683506080494226, "children": { "env_step": { "total": 1596.4265780539877, "count": 63647, "self": 1424.7984435249587, "children": { "SubprocessEnvManager._take_step": { "total": 170.66241646803428, "count": 63647, "self": 5.090897313039477, "children": { "TorchPolicy.evaluate": { "total": 165.5715191549948, "count": 62573, "self": 165.5715191549948 } } }, "workers": { "total": 0.9657180609947318, "count": 63647, "self": 0.0, "children": { "worker_root": { "total": 2284.5383960819518, "count": 63647, "is_parallel": true, "self": 982.4516564809842, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002339599000151793, "count": 1, "is_parallel": true, "self": 0.000870815999860497, "children": { "_process_rank_one_or_two_observation": { "total": 0.001468783000291296, "count": 8, "is_parallel": true, "self": 0.001468783000291296 } } }, "UnityEnvironment.step": { "total": 0.07431689399982133, "count": 1, "is_parallel": true, "self": 0.0005651749997923616, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005427040000540728, "count": 1, "is_parallel": true, "self": 0.0005427040000540728 }, "communicator.exchange": { "total": 0.07157134099998075, "count": 1, "is_parallel": true, "self": 0.07157134099998075 }, "steps_from_proto": { "total": 0.0016376739999941492, "count": 1, "is_parallel": true, "self": 0.0004172089998064621, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012204650001876871, "count": 8, "is_parallel": true, "self": 0.0012204650001876871 } } } } } } }, "UnityEnvironment.step": { "total": 1302.0867396009676, "count": 63646, "is_parallel": true, "self": 33.15473731183192, "children": { "UnityEnvironment._generate_step_input": { "total": 24.03225522196908, "count": 63646, "is_parallel": true, "self": 24.03225522196908 }, "communicator.exchange": { "total": 1143.3972427610306, "count": 63646, "is_parallel": true, "self": 1143.3972427610306 }, "steps_from_proto": { "total": 101.50250430613596, "count": 63646, "is_parallel": true, "self": 21.568221875038944, "children": { "_process_rank_one_or_two_observation": { "total": 79.93428243109702, "count": 509168, "is_parallel": true, "self": 79.93428243109702 } } } } } } } } } } }, "trainer_advance": { "total": 688.2658024439565, "count": 63647, "self": 3.0796021269979974, "children": { "process_trajectory": { "total": 130.84424155796478, "count": 63647, "self": 130.64059839196443, "children": { "RLTrainer._checkpoint": { "total": 0.20364316600034726, "count": 2, "self": 0.20364316600034726 } } }, "_update_policy": { "total": 554.3419587589938, "count": 439, "self": 302.23017903699065, "children": { "TorchPPOOptimizer.update": { "total": 252.11177972200312, "count": 22839, "self": 252.11177972200312 } } } } } } }, "trainer_threads": { "total": 1.1299998732283711e-06, "count": 1, "self": 1.1299998732283711e-06 }, "TrainerController._save_models": { "total": 0.095448690000012, "count": 1, "self": 0.0012910859995827195, "children": { "RLTrainer._checkpoint": { "total": 0.09415760400042927, "count": 1, "self": 0.09415760400042927 } } } } } } }