{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8461726903915405, "min": 0.8461726903915405, "max": 1.414008378982544, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 25358.103515625, "min": 25358.103515625, "max": 42895.359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.016819939017295837, "min": -0.10268987715244293, "max": 0.09874029457569122, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -4.087244987487793, "min": -24.645570755004883, "max": 23.40144920349121, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0020752272102981806, "min": 0.0003245932748541236, "max": 0.13551963865756989, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5042802095413208, "min": 0.07887616753578186, "max": 32.66023254394531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04631546648064007, "min": 0.042549973514507566, "max": 0.053452001537709515, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.694731997209601, "min": 0.3741640107639666, "max": 0.7172374971258384, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.002183124153553864, "min": 9.932698567237635e-05, "max": 0.00589265817392033, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03274686230330796, "min": 0.0011919238280685162, "max": 0.06252849771226465, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4637175121266655e-06, "min": 7.4637175121266655e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011195576268189998, "min": 0.00011195576268189998, "max": 0.0031163728612090998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248787333333335, "min": 0.10248787333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373181000000002, "min": 1.3886848, "max": 2.3070616999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000258538546, "min": 0.000258538546, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038780781899999998, "min": 0.0038780781899999998, "max": 0.10389521091, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00558899063616991, "min": 0.00558899063616991, "max": 0.19025906920433044, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08383485674858093, "min": 0.07978837192058563, "max": 1.3318134546279907, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 932.71875, "min": 844.5882352941177, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29847.0, "min": 15984.0, "max": 32711.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.5109515650705858, "min": -1.0000000521540642, "max": -0.07279379875399172, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.86140164732933, "min": -32.000001668930054, "max": -2.329401560127735, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.5109515650705858, "min": -1.0000000521540642, "max": -0.07279379875399172, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.86140164732933, "min": -32.000001668930054, "max": -2.329401560127735, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05516924144467339, "min": 0.049215435854207235, "max": 4.136290749069303, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8205849676742218, "min": 1.6733248190430459, "max": 66.18065198510885, "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": "1679312706", "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 --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": "1679314580" }, "total": 1874.304028635, "count": 1, "self": 0.4906757760002165, "children": { "run_training.setup": { "total": 0.17817938299981506, "count": 1, "self": 0.17817938299981506 }, "TrainerController.start_learning": { "total": 1873.6351734759999, "count": 1, "self": 1.2669125049778813, "children": { "TrainerController._reset_env": { "total": 9.510931704000086, "count": 1, "self": 9.510931704000086 }, "TrainerController.advance": { "total": 1862.7600726720218, "count": 63105, "self": 1.4193242559852024, "children": { "env_step": { "total": 1349.4002595750367, "count": 63105, "self": 1243.2931881100253, "children": { "SubprocessEnvManager._take_step": { "total": 105.30665478300853, "count": 63105, "self": 4.676305899054341, "children": { "TorchPolicy.evaluate": { "total": 100.63034888395418, "count": 62571, "self": 100.63034888395418 } } }, "workers": { "total": 0.8004166820028331, "count": 63105, "self": 0.0, "children": { "worker_root": { "total": 1869.4090488839304, "count": 63105, "is_parallel": true, "self": 738.3332849848771, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0065372920000754675, "count": 1, "is_parallel": true, "self": 0.004444473999683396, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020928180003920716, "count": 8, "is_parallel": true, "self": 0.0020928180003920716 } } }, "UnityEnvironment.step": { "total": 0.04867346099990755, "count": 1, "is_parallel": true, "self": 0.0005474999998114072, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005494070001077489, "count": 1, "is_parallel": true, "self": 0.0005494070001077489 }, "communicator.exchange": { "total": 0.04577318900010141, "count": 1, "is_parallel": true, "self": 0.04577318900010141 }, "steps_from_proto": { "total": 0.0018033649998869805, "count": 1, "is_parallel": true, "self": 0.00041887499992299126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013844899999639892, "count": 8, "is_parallel": true, "self": 0.0013844899999639892 } } } } } } }, "UnityEnvironment.step": { "total": 1131.0757638990533, "count": 63104, "is_parallel": true, "self": 31.357307215032733, "children": { "UnityEnvironment._generate_step_input": { "total": 22.648371875005523, "count": 63104, "is_parallel": true, "self": 22.648371875005523 }, "communicator.exchange": { "total": 986.133984394018, "count": 63104, "is_parallel": true, "self": 986.133984394018 }, "steps_from_proto": { "total": 90.9361004149971, "count": 63104, "is_parallel": true, "self": 19.310330113019518, "children": { "_process_rank_one_or_two_observation": { "total": 71.62577030197758, "count": 504832, "is_parallel": true, "self": 71.62577030197758 } } } } } } } } } } }, "trainer_advance": { "total": 511.94048884099993, "count": 63105, "self": 2.3811737540781905, "children": { "process_trajectory": { "total": 113.69874627892841, "count": 63105, "self": 113.47883223892836, "children": { "RLTrainer._checkpoint": { "total": 0.21991404000004877, "count": 2, "self": 0.21991404000004877 } } }, "_update_policy": { "total": 395.86056880799333, "count": 434, "self": 296.41690664198654, "children": { "TorchPPOOptimizer.update": { "total": 99.44366216600679, "count": 11247, "self": 99.44366216600679 } } } } } } }, "trainer_threads": { "total": 9.020000106829684e-07, "count": 1, "self": 9.020000106829684e-07 }, "TrainerController._save_models": { "total": 0.09725569300007919, "count": 1, "self": 0.0014408860001822177, "children": { "RLTrainer._checkpoint": { "total": 0.09581480699989697, "count": 1, "self": 0.09581480699989697 } } } } } } }