{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4831050634384155, "min": 0.4831050634384155, "max": 1.4233323335647583, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14578.1787109375, "min": 14498.134765625, "max": 43178.2109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989947.0, "min": 29952.0, "max": 989947.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989947.0, "min": 29952.0, "max": 989947.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5024935603141785, "min": -0.1060933768749237, "max": 0.5397955179214478, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.6732635498047, "min": -25.46240997314453, "max": 152.2223358154297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.0924036502838135, "min": -1.0924036502838135, "max": 1.003419280052185, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -294.948974609375, "min": -294.948974609375, "max": 282.9642333984375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06667162192450947, "min": 0.06475877700727167, "max": 0.07413618619068064, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9334027069431325, "min": 0.48422459194763834, "max": 1.0532008580145582, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.12208561804351013, "min": 5.580458452131456e-05, "max": 0.12208561804351013, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.7091986526091418, "min": 0.0007254595987770892, "max": 1.7091986526091418, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5364617735928535e-06, "min": 7.5364617735928535e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010551046483029995, "min": 0.00010551046483029995, "max": 0.0036325906891364994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251212142857144, "min": 0.10251212142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351697, "min": 1.3886848, "max": 2.6108635000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002609609307142857, "min": 0.0002609609307142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00365345303, "min": 0.00365345303, "max": 0.12110526365000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011456632055342197, "min": 0.011378226801753044, "max": 0.43440574407577515, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1603928506374359, "min": 0.15929517149925232, "max": 3.0408401489257812, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 370.2911392405063, "min": 349.97777777777776, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29253.0, "min": 15984.0, "max": 33547.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6073999773615446, "min": -1.0000000521540642, "max": 1.6073999773615446, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.37719823420048, "min": -31.991201639175415, "max": 136.49859823286533, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6073999773615446, "min": -1.0000000521540642, "max": 1.6073999773615446, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.37719823420048, "min": -31.991201639175415, "max": 136.49859823286533, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043517399918831266, "min": 0.043517399918831266, "max": 8.619039500132203, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3943571936688386, "min": 3.3943571936688386, "max": 137.90463200211525, "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": "1684555431", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --force --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1684557574" }, "total": 2143.455808337, "count": 1, "self": 0.48315078899986474, "children": { "run_training.setup": { "total": 0.04446476300017821, "count": 1, "self": 0.04446476300017821 }, "TrainerController.start_learning": { "total": 2142.9281927849997, "count": 1, "self": 1.4184925150693743, "children": { "TrainerController._reset_env": { "total": 3.833995287000107, "count": 1, "self": 3.833995287000107 }, "TrainerController.advance": { "total": 2137.57961892593, "count": 63628, "self": 1.3863245959728374, "children": { "env_step": { "total": 1500.5556957669646, "count": 63628, "self": 1390.585431720011, "children": { "SubprocessEnvManager._take_step": { "total": 109.13829189495618, "count": 63628, "self": 4.717797166879791, "children": { "TorchPolicy.evaluate": { "total": 104.42049472807639, "count": 62563, "self": 104.42049472807639 } } }, "workers": { "total": 0.8319721519974337, "count": 63628, "self": 0.0, "children": { "worker_root": { "total": 2138.2322675059045, "count": 63628, "is_parallel": true, "self": 859.1837319469869, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018296660000487464, "count": 1, "is_parallel": true, "self": 0.0005732049999096489, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012564610001390975, "count": 8, "is_parallel": true, "self": 0.0012564610001390975 } } }, "UnityEnvironment.step": { "total": 0.05965228000013667, "count": 1, "is_parallel": true, "self": 0.000568483000733977, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005028710002079606, "count": 1, "is_parallel": true, "self": 0.0005028710002079606 }, "communicator.exchange": { "total": 0.056657944999642496, "count": 1, "is_parallel": true, "self": 0.056657944999642496 }, "steps_from_proto": { "total": 0.0019229809995522373, "count": 1, "is_parallel": true, "self": 0.00038204099882932496, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015409400007229124, "count": 8, "is_parallel": true, "self": 0.0015409400007229124 } } } } } } }, "UnityEnvironment.step": { "total": 1279.0485355589176, "count": 63627, "is_parallel": true, "self": 31.581052937798177, "children": { "UnityEnvironment._generate_step_input": { "total": 22.449716795073073, "count": 63627, "is_parallel": true, "self": 22.449716795073073 }, "communicator.exchange": { "total": 1127.5460388189763, "count": 63627, "is_parallel": true, "self": 1127.5460388189763 }, "steps_from_proto": { "total": 97.47172700707006, "count": 63627, "is_parallel": true, "self": 19.87169319470786, "children": { "_process_rank_one_or_two_observation": { "total": 77.6000338123622, "count": 509016, "is_parallel": true, "self": 77.6000338123622 } } } } } } } } } } }, "trainer_advance": { "total": 635.6375985629925, "count": 63628, "self": 2.559250692036585, "children": { "process_trajectory": { "total": 104.57459729296124, "count": 63628, "self": 104.32702443396101, "children": { "RLTrainer._checkpoint": { "total": 0.24757285900022907, "count": 2, "self": 0.24757285900022907 } } }, "_update_policy": { "total": 528.5037505779947, "count": 451, "self": 342.7510682279749, "children": { "TorchPPOOptimizer.update": { "total": 185.75268235001977, "count": 22845, "self": 185.75268235001977 } } } } } } }, "trainer_threads": { "total": 9.109999155043624e-07, "count": 1, "self": 9.109999155043624e-07 }, "TrainerController._save_models": { "total": 0.09608514600040508, "count": 1, "self": 0.001926193000144849, "children": { "RLTrainer._checkpoint": { "total": 0.09415895300026023, "count": 1, "self": 0.09415895300026023 } } } } } } }