{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3363150656223297, "min": 0.3363150656223297, "max": 1.3886160850524902, "count": 30 }, "Pyramids.Policy.Entropy.sum": { "value": 10024.8798828125, "min": 10024.8798828125, "max": 42125.05859375, "count": 30 }, "Pyramids.Step.mean": { "value": 899900.0, "min": 29952.0, "max": 899900.0, "count": 30 }, "Pyramids.Step.sum": { "value": 899900.0, "min": 29952.0, "max": 899900.0, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6571280360221863, "min": -0.06938806176185608, "max": 0.6803486347198486, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 192.53851318359375, "min": -16.722522735595703, "max": 193.8993682861328, "count": 30 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027511505410075188, "min": -0.00782816857099533, "max": 0.3895452618598938, "count": 30 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.060871124267578, "min": -2.090121030807495, "max": 93.49085998535156, "count": 30 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06669218785844284, "min": 0.06363652978598365, "max": 0.07378624560991667, "count": 30 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9336906300181997, "min": 0.48405376985273063, "max": 1.0714092923056646, "count": 30 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018474384820676037, "min": 0.0018855194301808048, "max": 0.018474384820676037, "count": 30 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2586413874894645, "min": 0.01445070398136815, "max": 0.2586413874894645, "count": 30 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.765836506658729e-06, "min": 4.765836506658729e-06, "max": 0.000294611811319873, "count": 30 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.672171109322222e-05, "min": 6.672171109322222e-05, "max": 0.003569797543400889, "count": 30 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10158857936507938, "min": 0.10158857936507938, "max": 0.1982039365079365, "count": 30 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4222401111111114, "min": 1.3656817777777779, "max": 2.589932444444444, "count": 30 }, "Pyramids.Policy.Beta.mean": { "value": 0.00016869907857142852, "min": 0.00016869907857142852, "max": 0.00982057325714286, "count": 30 }, "Pyramids.Policy.Beta.sum": { "value": 0.0023617870999999993, "min": 0.0023617870999999993, "max": 0.11901425119999999, "count": 30 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01585100032389164, "min": 0.01585100032389164, "max": 0.5556565523147583, "count": 30 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22191400825977325, "min": 0.22191400825977325, "max": 3.8895959854125977, "count": 30 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 264.1025641025641, "min": 264.1025641025641, "max": 999.0, "count": 30 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30900.0, "min": 15984.0, "max": 32949.0, "count": 30 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7358974228557358, "min": -1.0000000521540642, "max": 1.7358974228557358, "count": 30 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 203.0999984741211, "min": -32.000001668930054, "max": 203.0999984741211, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7358974228557358, "min": -1.0000000521540642, "max": 1.7358974228557358, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 203.0999984741211, "min": -32.000001668930054, "max": 203.0999984741211, "count": 30 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043666166431493424, "min": 0.043666166431493424, "max": 10.019153380766511, "count": 30 }, "Pyramids.Policy.RndReward.sum": { "value": 5.10894147248473, "min": 4.835512494188151, "max": 160.30645409226418, "count": 30 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677654498", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677656814" }, "total": 2315.850000083, "count": 1, "self": 0.5937301869998919, "children": { "run_training.setup": { "total": 0.11864076599999862, "count": 1, "self": 0.11864076599999862 }, "TrainerController.start_learning": { "total": 2315.13762913, "count": 1, "self": 1.492196666010841, "children": { "TrainerController._reset_env": { "total": 9.223114656999996, "count": 1, "self": 9.223114656999996 }, "TrainerController.advance": { "total": 2304.329678692989, "count": 57860, "self": 1.531444261017441, "children": { "env_step": { "total": 1582.9958713150086, "count": 57860, "self": 1467.5065710539936, "children": { "SubprocessEnvManager._take_step": { "total": 114.58860219099438, "count": 57860, "self": 4.636051852962055, "children": { "TorchPolicy.evaluate": { "total": 109.95255033803232, "count": 56308, "self": 37.01318645005085, "children": { "TorchPolicy.sample_actions": { "total": 72.93936388798147, "count": 56308, "self": 72.93936388798147 } } } } }, "workers": { "total": 0.9006980700205531, "count": 57860, "self": 0.0, "children": { "worker_root": { "total": 2309.683474066036, "count": 57860, "is_parallel": true, "self": 961.5115075220251, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004885869000077037, "count": 1, "is_parallel": true, "self": 0.0036196290002408205, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012662399998362162, "count": 8, "is_parallel": true, "self": 0.0012662399998362162 } } }, "UnityEnvironment.step": { "total": 0.050968650999948295, "count": 1, "is_parallel": true, "self": 0.0005448979999300718, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005186580000327012, "count": 1, "is_parallel": true, "self": 0.0005186580000327012 }, "communicator.exchange": { "total": 0.04828308799994829, "count": 1, "is_parallel": true, "self": 0.04828308799994829 }, "steps_from_proto": { "total": 0.0016220070000372289, "count": 1, "is_parallel": true, "self": 0.0004398809999202058, "children": { "_process_rank_one_or_two_observation": { "total": 0.001182126000117023, "count": 8, "is_parallel": true, "self": 0.001182126000117023 } } } } } } }, "UnityEnvironment.step": { "total": 1348.171966544011, "count": 57859, "is_parallel": true, "self": 31.466340030994616, "children": { "UnityEnvironment._generate_step_input": { "total": 22.358787438039258, "count": 57859, "is_parallel": true, "self": 22.358787438039258 }, "communicator.exchange": { "total": 1203.5424513670096, "count": 57859, "is_parallel": true, "self": 1203.5424513670096 }, "steps_from_proto": { "total": 90.80438770796775, "count": 57859, "is_parallel": true, "self": 22.259620733937368, "children": { "_process_rank_one_or_two_observation": { "total": 68.54476697403038, "count": 462872, "is_parallel": true, "self": 68.54476697403038 } } } } } } } } } } }, "trainer_advance": { "total": 719.8023631169632, "count": 57860, "self": 2.859240361971615, "children": { "process_trajectory": { "total": 157.95503435098908, "count": 57860, "self": 157.7955492619892, "children": { "RLTrainer._checkpoint": { "total": 0.15948508899987246, "count": 1, "self": 0.15948508899987246 } } }, "_update_policy": { "total": 558.9880884040025, "count": 404, "self": 219.1148148969927, "children": { "TorchPPOOptimizer.update": { "total": 339.8732735070098, "count": 20502, "self": 339.8732735070098 } } } } } } }, "trainer_threads": { "total": 8.560000424040481e-07, "count": 1, "self": 8.560000424040481e-07 }, "TrainerController._save_models": { "total": 0.09263825800007908, "count": 1, "self": 0.001377156000216928, "children": { "RLTrainer._checkpoint": { "total": 0.09126110199986215, "count": 1, "self": 0.09126110199986215 } } } } } } }