{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34473156929016113, "min": 0.34473156929016113, "max": 1.3521031141281128, "count": 51 }, "Pyramids.Policy.Entropy.sum": { "value": 10314.3681640625, "min": 10314.3681640625, "max": 41017.3984375, "count": 51 }, "Pyramids.Step.mean": { "value": 1529955.0, "min": 29952.0, "max": 1529955.0, "count": 51 }, "Pyramids.Step.sum": { "value": 1529955.0, "min": 29952.0, "max": 1529955.0, "count": 51 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6633832454681396, "min": -0.1136084496974945, "max": 0.746944010257721, "count": 51 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.747314453125, "min": -27.379636764526367, "max": 216.61376953125, "count": 51 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003732958808541298, "min": -0.03096938692033291, "max": 0.7258607149124146, "count": 51 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.0452284812927246, "min": -8.516581535339355, "max": 172.02899169921875, "count": 51 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06778064754554163, "min": 0.06472327878111087, "max": 0.07380177942292142, "count": 51 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9489290656375827, "min": 0.5092565117175717, "max": 1.0884144141957364, "count": 51 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011963429751610955, "min": 0.0006056632106170908, "max": 0.016267943262256758, "count": 51 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16748801652255338, "min": 0.008479284948639271, "max": 0.22775120567159463, "count": 51 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014849881478612616, "min": 0.00014849881478612616, "max": 0.00029838354339596195, "count": 51 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020789834070057663, "min": 0.0020789834070057663, "max": 0.003937268187577333, "count": 51 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14949958809523808, "min": 0.14949958809523808, "max": 0.19946118095238097, "count": 51 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.092994233333333, "min": 1.3962282666666668, "max": 2.812422666666667, "count": 51 }, "Pyramids.Policy.Beta.mean": { "value": 0.004955008850714286, "min": 0.004955008850714286, "max": 0.009946171977142856, "count": 51 }, "Pyramids.Policy.Beta.sum": { "value": 0.06937012391, "min": 0.06937012391, "max": 0.13126102439999998, "count": 51 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005452983547002077, "min": 0.005452983547002077, "max": 0.5388436317443848, "count": 51 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07634177058935165, "min": 0.07634177058935165, "max": 3.7719054222106934, "count": 51 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 319.0860215053763, "min": 263.77477477477476, "max": 999.0, "count": 51 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29675.0, "min": 15984.0, "max": 33237.0, "count": 51 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5733548271399673, "min": -1.0000000521540642, "max": 1.712514511285684, "count": 51 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 146.32199892401695, "min": -29.90400167554617, "max": 200.36419782042503, "count": 51 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5733548271399673, "min": -1.0000000521540642, "max": 1.712514511285684, "count": 51 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 146.32199892401695, "min": -29.90400167554617, "max": 200.36419782042503, "count": 51 }, "Pyramids.Policy.RndReward.mean": { "value": 0.018114594037122574, "min": 0.01612276891833412, "max": 10.815195646137, "count": 51 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6846572454523994, "min": 1.6767679675067484, "max": 173.043130338192, "count": 51 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 51 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 51 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673773724", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673776997" }, "total": 3272.714554587, "count": 1, "self": 0.3260815249996085, "children": { "run_training.setup": { "total": 0.10747377200004848, "count": 1, "self": 0.10747377200004848 }, "TrainerController.start_learning": { "total": 3272.28099929, "count": 1, "self": 1.7478393000883443, "children": { "TrainerController._reset_env": { "total": 6.456248368999923, "count": 1, "self": 6.456248368999923 }, "TrainerController.advance": { "total": 3263.923110835912, "count": 99116, "self": 1.8734890727714628, "children": { "env_step": { "total": 2243.3135783931, "count": 99116, "self": 2090.317234769119, "children": { "SubprocessEnvManager._take_step": { "total": 151.90298767602303, "count": 99116, "self": 6.355907059004494, "children": { "TorchPolicy.evaluate": { "total": 145.54708061701854, "count": 96305, "self": 49.81885900902057, "children": { "TorchPolicy.sample_actions": { "total": 95.72822160799797, "count": 96305, "self": 95.72822160799797 } } } } }, "workers": { "total": 1.0933559479581163, "count": 99115, "self": 0.0, "children": { "worker_root": { "total": 3265.773710493011, "count": 99115, "is_parallel": true, "self": 1321.1656346529653, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018128369999885763, "count": 1, "is_parallel": true, "self": 0.0006593179998617416, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011535190001268347, "count": 8, "is_parallel": true, "self": 0.0011535190001268347 } } }, "UnityEnvironment.step": { "total": 0.046005367000134356, "count": 1, "is_parallel": true, "self": 0.0005876929999431013, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045106200013833586, "count": 1, "is_parallel": true, "self": 0.00045106200013833586 }, "communicator.exchange": { "total": 0.04313725900010468, "count": 1, "is_parallel": true, "self": 0.04313725900010468 }, "steps_from_proto": { "total": 0.0018293529999482416, "count": 1, "is_parallel": true, "self": 0.00048235599979307153, "children": { "_process_rank_one_or_two_observation": { "total": 0.00134699700015517, "count": 8, "is_parallel": true, "self": 0.00134699700015517 } } } } } } }, "UnityEnvironment.step": { "total": 1944.6080758400458, "count": 99114, "is_parallel": true, "self": 43.14153665485469, "children": { "UnityEnvironment._generate_step_input": { "total": 34.81640416908317, "count": 99114, "is_parallel": true, "self": 34.81640416908317 }, "communicator.exchange": { "total": 1711.7962709400717, "count": 99114, "is_parallel": true, "self": 1711.7962709400717 }, "steps_from_proto": { "total": 154.8538640760362, "count": 99114, "is_parallel": true, "self": 33.38475969502156, "children": { "_process_rank_one_or_two_observation": { "total": 121.46910438101463, "count": 792912, "is_parallel": true, "self": 121.46910438101463 } } } } } } } } } } }, "trainer_advance": { "total": 1018.7360433700403, "count": 99115, "self": 3.4019072830467394, "children": { "process_trajectory": { "total": 220.4935685599869, "count": 99115, "self": 220.20375296698762, "children": { "RLTrainer._checkpoint": { "total": 0.2898155929992754, "count": 3, "self": 0.2898155929992754 } } }, "_update_policy": { "total": 794.8405675270067, "count": 704, "self": 305.5789057240611, "children": { "TorchPPOOptimizer.update": { "total": 489.2616618029456, "count": 35181, "self": 489.2616618029456 } } } } } } }, "trainer_threads": { "total": 1.4349998309626244e-06, "count": 1, "self": 1.4349998309626244e-06 }, "TrainerController._save_models": { "total": 0.15379934999964462, "count": 1, "self": 0.003727043000253616, "children": { "RLTrainer._checkpoint": { "total": 0.150072306999391, "count": 1, "self": 0.150072306999391 } } } } } } }