{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5660867094993591, "min": 0.554049015045166, "max": 1.4703035354614258, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16910.142578125, "min": 16754.44140625, "max": 44603.12890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29874.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29874.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.026042358949780464, "min": -0.10206277668476105, "max": 0.06799918413162231, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 6.4064202308654785, "min": -24.597129821777344, "max": 16.727798461914062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0075026145204901695, "min": -0.0061217197217047215, "max": 0.30238455533981323, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.845643162727356, "min": -1.5059430599212646, "max": 72.87467956542969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06413571656588171, "min": 0.06413571656588171, "max": 0.07321951957525495, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8979000319223439, "min": 0.5000715416025814, "max": 1.0388673787917164, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.005869294582623274, "min": 0.00045276917492287995, "max": 0.006556808983987138, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.08217012415672584, "min": 0.00498046092415168, "max": 0.09179532577581993, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.4270547159000002e-06, "min": 2.4270547159000002e-06, "max": 9.838354447360002e-05, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.3978766022600006e-05, "min": 3.3978766022600006e-05, "max": 0.0011691601308401, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242695714285714, "min": 0.10242695714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339774, "min": 1.3886848, "max": 2.5691599000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025245301857142866, "min": 0.00025245301857142866, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003534342260000001, "min": 0.003534342260000001, "max": 0.11693907401000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016322756186127663, "min": 0.016322756186127663, "max": 0.45837831497192383, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22851857542991638, "min": 0.22851857542991638, "max": 3.208648204803467, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 801.09375, "min": 757.1515151515151, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 25635.0, "min": 16801.0, "max": 33096.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.13601871114224195, "min": -0.9999806972280625, "max": 0.33352724372437503, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 4.3525987565517426, "min": -30.99940161406994, "max": 11.006399042904377, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.13601871114224195, "min": -0.9999806972280625, "max": 0.33352724372437503, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 4.3525987565517426, "min": -30.99940161406994, "max": 11.006399042904377, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.13575547446816927, "min": 0.13575547446816927, "max": 8.459434292772237, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.344175182981417, "min": 4.344175182981417, "max": 143.81038297712803, "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": "1681928618", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681930726" }, "total": 2108.393649072, "count": 1, "self": 0.49360840300005293, "children": { "run_training.setup": { "total": 0.1349265710000509, "count": 1, "self": 0.1349265710000509 }, "TrainerController.start_learning": { "total": 2107.7651140979997, "count": 1, "self": 1.624797059906541, "children": { "TrainerController._reset_env": { "total": 3.732865678999815, "count": 1, "self": 3.732865678999815 }, "TrainerController.advance": { "total": 2102.3036475040935, "count": 63237, "self": 1.6385663731352906, "children": { "env_step": { "total": 1462.634954482047, "count": 63237, "self": 1344.269540893071, "children": { "SubprocessEnvManager._take_step": { "total": 117.43343352196166, "count": 63237, "self": 5.2410621559229185, "children": { "TorchPolicy.evaluate": { "total": 112.19237136603874, "count": 62559, "self": 112.19237136603874 } } }, "workers": { "total": 0.931980067014365, "count": 63237, "self": 0.0, "children": { "worker_root": { "total": 2102.4071251949395, "count": 63237, "is_parallel": true, "self": 880.8950439829671, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017498520001026918, "count": 1, "is_parallel": true, "self": 0.0005726539995976054, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011771980005050864, "count": 8, "is_parallel": true, "self": 0.0011771980005050864 } } }, "UnityEnvironment.step": { "total": 0.0689854220001962, "count": 1, "is_parallel": true, "self": 0.0006268870001804316, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005241779999778373, "count": 1, "is_parallel": true, "self": 0.0005241779999778373 }, "communicator.exchange": { "total": 0.06475146000002496, "count": 1, "is_parallel": true, "self": 0.06475146000002496 }, "steps_from_proto": { "total": 0.003082897000012963, "count": 1, "is_parallel": true, "self": 0.0004352429996288265, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026476540003841365, "count": 8, "is_parallel": true, "self": 0.0026476540003841365 } } } } } } }, "UnityEnvironment.step": { "total": 1221.5120812119724, "count": 63236, "is_parallel": true, "self": 33.609199948826245, "children": { "UnityEnvironment._generate_step_input": { "total": 25.028001143049096, "count": 63236, "is_parallel": true, "self": 25.028001143049096 }, "communicator.exchange": { "total": 1061.0630888740818, "count": 63236, "is_parallel": true, "self": 1061.0630888740818 }, "steps_from_proto": { "total": 101.81179124601522, "count": 63236, "is_parallel": true, "self": 22.103558426230165, "children": { "_process_rank_one_or_two_observation": { "total": 79.70823281978505, "count": 505888, "is_parallel": true, "self": 79.70823281978505 } } } } } } } } } } }, "trainer_advance": { "total": 638.0301266489114, "count": 63237, "self": 2.7955249619283222, "children": { "process_trajectory": { "total": 111.75122368298184, "count": 63237, "self": 111.52800133398227, "children": { "RLTrainer._checkpoint": { "total": 0.22322234899957039, "count": 2, "self": 0.22322234899957039 } } }, "_update_policy": { "total": 523.4833780040012, "count": 449, "self": 336.5329811050178, "children": { "TorchPPOOptimizer.update": { "total": 186.9503968989834, "count": 22767, "self": 186.9503968989834 } } } } } } }, "trainer_threads": { "total": 9.260002116207033e-07, "count": 1, "self": 9.260002116207033e-07 }, "TrainerController._save_models": { "total": 0.10380292899981214, "count": 1, "self": 0.0015779899999870395, "children": { "RLTrainer._checkpoint": { "total": 0.1022249389998251, "count": 1, "self": 0.1022249389998251 } } } } } } }