{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3005628287792206, "min": 0.3005628287792206, "max": 1.5464361906051636, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8968.794921875, "min": 8968.794921875, "max": 46912.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6635273694992065, "min": -0.2295599728822708, "max": 0.6673892140388489, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 191.09588623046875, "min": -54.40571212768555, "max": 194.87765502929688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0032222382724285126, "min": -0.003791572293266654, "max": 0.183832049369812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.9280046224594116, "min": -1.0730149745941162, "max": 43.56819534301758, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06745573089435873, "min": 0.06554436716096997, "max": 0.07357757838200145, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9443802325210223, "min": 0.48936212894335474, "max": 1.0945060158070798, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01599682465755558, "min": 0.0008600193549603384, "max": 0.016817160171783706, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22395554520577812, "min": 0.01032023225952406, "max": 0.2354402424049719, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.548183198257145e-06, "min": 7.548183198257145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010567456477560003, "min": 0.00010567456477560003, "max": 0.0034932142355952995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251602857142857, "min": 0.10251602857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352243999999998, "min": 1.3691136000000002, "max": 2.527537, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002613512542857144, "min": 0.0002613512542857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036589175600000015, "min": 0.0036589175600000015, "max": 0.11645402953, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011074488051235676, "min": 0.011074488051235676, "max": 0.2865247130393982, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.155042827129364, "min": 0.155042827129364, "max": 2.0056729316711426, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 268.24545454545455, "min": 268.24545454545455, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29507.0, "min": 15984.0, "max": 33237.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6953799801793965, "min": -1.0000000521540642, "max": 1.696485173922998, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 186.49179781973362, "min": -32.000001668930054, "max": 186.49179781973362, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6953799801793965, "min": -1.0000000521540642, "max": 1.696485173922998, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 186.49179781973362, "min": -32.000001668930054, "max": 186.49179781973362, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030591719797832245, "min": 0.030591719797832245, "max": 5.5918001448735595, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.365089177761547, "min": 3.365089177761547, "max": 89.46880231797695, "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": "1690635471", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --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": "1690637755" }, "total": 2284.0512312260003, "count": 1, "self": 0.47692793800024447, "children": { "run_training.setup": { "total": 0.03493957499995304, "count": 1, "self": 0.03493957499995304 }, "TrainerController.start_learning": { "total": 2283.539363713, "count": 1, "self": 1.5102357120481429, "children": { "TrainerController._reset_env": { "total": 4.183141120000073, "count": 1, "self": 4.183141120000073 }, "TrainerController.advance": { "total": 2277.7530328649514, "count": 63955, "self": 1.4050267450597858, "children": { "env_step": { "total": 1608.9710600449548, "count": 63955, "self": 1498.356526001895, "children": { "SubprocessEnvManager._take_step": { "total": 109.74133630505503, "count": 63955, "self": 4.7717513360835255, "children": { "TorchPolicy.evaluate": { "total": 104.9695849689715, "count": 62548, "self": 104.9695849689715 } } }, "workers": { "total": 0.8731977380048193, "count": 63955, "self": 0.0, "children": { "worker_root": { "total": 2278.1644410989584, "count": 63955, "is_parallel": true, "self": 895.8590886010215, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019311549999656563, "count": 1, "is_parallel": true, "self": 0.0005928380010118417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013383169989538146, "count": 8, "is_parallel": true, "self": 0.0013383169989538146 } } }, "UnityEnvironment.step": { "total": 0.04916265800011388, "count": 1, "is_parallel": true, "self": 0.0006201239993970376, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005090690001452458, "count": 1, "is_parallel": true, "self": 0.0005090690001452458 }, "communicator.exchange": { "total": 0.046180253000329685, "count": 1, "is_parallel": true, "self": 0.046180253000329685 }, "steps_from_proto": { "total": 0.0018532120002419106, "count": 1, "is_parallel": true, "self": 0.0003748059993995412, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014784060008423694, "count": 8, "is_parallel": true, "self": 0.0014784060008423694 } } } } } } }, "UnityEnvironment.step": { "total": 1382.3053524979368, "count": 63954, "is_parallel": true, "self": 34.71430572184954, "children": { "UnityEnvironment._generate_step_input": { "total": 22.966035557976284, "count": 63954, "is_parallel": true, "self": 22.966035557976284 }, "communicator.exchange": { "total": 1221.3741368940978, "count": 63954, "is_parallel": true, "self": 1221.3741368940978 }, "steps_from_proto": { "total": 103.25087432401324, "count": 63954, "is_parallel": true, "self": 21.19978621487735, "children": { "_process_rank_one_or_two_observation": { "total": 82.05108810913589, "count": 511632, "is_parallel": true, "self": 82.05108810913589 } } } } } } } } } } }, "trainer_advance": { "total": 667.3769460749368, "count": 63955, "self": 2.6423888718468334, "children": { "process_trajectory": { "total": 112.5884819320845, "count": 63955, "self": 112.37879675208433, "children": { "RLTrainer._checkpoint": { "total": 0.20968518000017866, "count": 2, "self": 0.20968518000017866 } } }, "_update_policy": { "total": 552.1460752710054, "count": 449, "self": 360.31417978799755, "children": { "TorchPPOOptimizer.update": { "total": 191.83189548300788, "count": 22818, "self": 191.83189548300788 } } } } } } }, "trainer_threads": { "total": 1.0140001904801466e-06, "count": 1, "self": 1.0140001904801466e-06 }, "TrainerController._save_models": { "total": 0.09295300200028578, "count": 1, "self": 0.0014710980003656005, "children": { "RLTrainer._checkpoint": { "total": 0.09148190399992018, "count": 1, "self": 0.09148190399992018 } } } } } } }