{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5123621225357056, "min": 0.5123621225357056, "max": 1.4478181600570679, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15379.0615234375, "min": 15379.0615234375, "max": 43921.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29921.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29921.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4854337275028229, "min": -0.0997934639453888, "max": 0.4942700266838074, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 133.97970581054688, "min": -23.95043182373047, "max": 137.90133666992188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03163745254278183, "min": -0.08903004229068756, "max": 0.3003970682621002, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.731937408447266, "min": -22.168479919433594, "max": 71.49449920654297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0700229547875804, "min": 0.06514275648471533, "max": 0.07275777092700833, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.050344321813706, "min": 0.5820621674160666, "max": 1.0727315721160267, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014101934525468903, "min": 0.00022611479645474091, "max": 0.017249060494623717, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21152901788203354, "min": 0.002939492353911632, "max": 0.24148684692473205, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.541037486353338e-06, "min": 7.541037486353338e-06, "max": 0.00029485035171655, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011311556229530007, "min": 0.00011311556229530007, "max": 0.0036091578969474, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251364666666668, "min": 0.10251364666666668, "max": 0.19828345, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377047000000001, "min": 1.4780487999999996, "max": 2.56906, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002611133020000002, "min": 0.0002611133020000002, "max": 0.009828516655000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003916699530000003, "min": 0.003916699530000003, "max": 0.12031495474000004, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008687824010848999, "min": 0.008687824010848999, "max": 0.3848576545715332, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13031736016273499, "min": 0.12434162199497223, "max": 3.0788612365722656, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 363.27710843373495, "min": 363.27710843373495, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30152.0, "min": 17231.0, "max": 32129.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4920915482812618, "min": -0.9999375534243882, "max": 1.5864698508058686, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.84359850734472, "min": -31.99800170958042, "max": 131.6769976168871, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4920915482812618, "min": -0.9999375534243882, "max": 1.5864698508058686, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.84359850734472, "min": -31.99800170958042, "max": 131.6769976168871, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03295600993722868, "min": 0.03295600993722868, "max": 7.681839644908905, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7353488247899804, "min": 2.553997143317247, "max": 138.2731136083603, "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": "1710083089", "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": "1710086284" }, "total": 3195.01157031, "count": 1, "self": 0.6300733689995468, "children": { "run_training.setup": { "total": 0.06851419999998143, "count": 1, "self": 0.06851419999998143 }, "TrainerController.start_learning": { "total": 3194.3129827410003, "count": 1, "self": 2.2751331170302365, "children": { "TrainerController._reset_env": { "total": 2.65920932899985, "count": 1, "self": 2.65920932899985 }, "TrainerController.advance": { "total": 3189.2779985089705, "count": 63692, "self": 2.511178440976437, "children": { "env_step": { "total": 2086.8873754649294, "count": 63692, "self": 1919.480604162808, "children": { "SubprocessEnvManager._take_step": { "total": 165.94684915208813, "count": 63692, "self": 7.073208622110087, "children": { "TorchPolicy.evaluate": { "total": 158.87364052997805, "count": 62550, "self": 158.87364052997805 } } }, "workers": { "total": 1.4599221500332078, "count": 63692, "self": 0.0, "children": { "worker_root": { "total": 3187.9435255730295, "count": 63692, "is_parallel": true, "self": 1456.6612255279651, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002442283000164025, "count": 1, "is_parallel": true, "self": 0.0007911520001471217, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016511310000169033, "count": 8, "is_parallel": true, "self": 0.0016511310000169033 } } }, "UnityEnvironment.step": { "total": 0.06408854899996186, "count": 1, "is_parallel": true, "self": 0.0007580870001220319, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034717799985628517, "count": 1, "is_parallel": true, "self": 0.00034717799985628517 }, "communicator.exchange": { "total": 0.06098799699998381, "count": 1, "is_parallel": true, "self": 0.06098799699998381 }, "steps_from_proto": { "total": 0.0019952869999997347, "count": 1, "is_parallel": true, "self": 0.0004401020000841527, "children": { "_process_rank_one_or_two_observation": { "total": 0.001555184999915582, "count": 8, "is_parallel": true, "self": 0.001555184999915582 } } } } } } }, "UnityEnvironment.step": { "total": 1731.2823000450644, "count": 63691, "is_parallel": true, "self": 51.14428572413635, "children": { "UnityEnvironment._generate_step_input": { "total": 27.494588453021834, "count": 63691, "is_parallel": true, "self": 27.494588453021834 }, "communicator.exchange": { "total": 1519.7950921569534, "count": 63691, "is_parallel": true, "self": 1519.7950921569534 }, "steps_from_proto": { "total": 132.84833371095283, "count": 63691, "is_parallel": true, "self": 28.326643442669365, "children": { "_process_rank_one_or_two_observation": { "total": 104.52169026828346, "count": 509528, "is_parallel": true, "self": 104.52169026828346 } } } } } } } } } } }, "trainer_advance": { "total": 1099.8794446030647, "count": 63692, "self": 4.565522936073876, "children": { "process_trajectory": { "total": 167.3749685549883, "count": 63692, "self": 167.08918786598815, "children": { "RLTrainer._checkpoint": { "total": 0.2857806890001484, "count": 2, "self": 0.2857806890001484 } } }, "_update_policy": { "total": 927.9389531120025, "count": 455, "self": 366.82047433003936, "children": { "TorchPPOOptimizer.update": { "total": 561.1184787819632, "count": 22767, "self": 561.1184787819632 } } } } } } }, "trainer_threads": { "total": 1.0009998732130043e-06, "count": 1, "self": 1.0009998732130043e-06 }, "TrainerController._save_models": { "total": 0.10064078499999596, "count": 1, "self": 0.002187648000472109, "children": { "RLTrainer._checkpoint": { "total": 0.09845313699952385, "count": 1, "self": 0.09845313699952385 } } } } } } }