{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7458287477493286, "min": 0.727414608001709, "max": 2.85223126411438, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7662.64453125, "min": 7033.3720703125, "max": 29209.69921875, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.26479721069336, "min": 0.2492729127407074, "max": 13.450989723205566, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2706.0185546875, "min": 48.358943939208984, "max": 2757.452880859375, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06691423289668427, "min": 0.05891830437986737, "max": 0.07612216455134901, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.33457116448342133, "min": 0.23567321751946949, "max": 0.36596765014224264, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19383960784065957, "min": 0.15512493756649942, "max": 0.28730727171196657, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9691980392032978, "min": 0.6204997502659977, "max": 1.436536358559833, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.050764903999999e-06, "min": 7.050764903999999e-06, "max": 0.00039278400180400006, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5253824519999994e-05, "min": 3.5253824519999994e-05, "max": 0.0018979200255199997, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666667, "min": 0.10176266666666667, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333333, "min": 0.42025066666666666, "max": 0.97448, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0049099804000000006, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.023726551999999998, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.12727272727273, "min": 3.909090909090909, "max": 26.490909090909092, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1437.0, "min": 172.0, "max": 1457.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.12727272727273, "min": 3.909090909090909, "max": 26.490909090909092, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1437.0, "min": 172.0, "max": 1457.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674161427", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1674162045" }, "total": 618.088052547, "count": 1, "self": 0.3889905179999005, "children": { "run_training.setup": { "total": 0.10986452800000279, "count": 1, "self": 0.10986452800000279 }, "TrainerController.start_learning": { "total": 617.5891975010001, "count": 1, "self": 0.8860399919860811, "children": { "TrainerController._reset_env": { "total": 9.801986700000043, "count": 1, "self": 9.801986700000043 }, "TrainerController.advance": { "total": 606.785239543014, "count": 27334, "self": 0.3734642200241751, "children": { "env_step": { "total": 606.4117753229898, "count": 27334, "self": 393.72409057097775, "children": { "SubprocessEnvManager._take_step": { "total": 212.31974939299778, "count": 27334, "self": 2.0385483009984, "children": { "TorchPolicy.evaluate": { "total": 210.28120109199938, "count": 27334, "self": 45.67885221200095, "children": { "TorchPolicy.sample_actions": { "total": 164.60234887999843, "count": 27334, "self": 164.60234887999843 } } } } }, "workers": { "total": 0.3679353590142682, "count": 27334, "self": 0.0, "children": { "worker_root": { "total": 615.6984564920157, "count": 27334, "is_parallel": true, "self": 297.7827426060029, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006307986000024357, "count": 1, "is_parallel": true, "self": 0.003799498999910611, "children": { "_process_rank_one_or_two_observation": { "total": 0.002508487000113746, "count": 10, "is_parallel": true, "self": 0.002508487000113746 } } }, "UnityEnvironment.step": { "total": 0.031759578999981386, "count": 1, "is_parallel": true, "self": 0.0005995049999683033, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002990680000038992, "count": 1, "is_parallel": true, "self": 0.0002990680000038992 }, "communicator.exchange": { "total": 0.029054891999976462, "count": 1, "is_parallel": true, "self": 0.029054891999976462 }, "steps_from_proto": { "total": 0.0018061140000327214, "count": 1, "is_parallel": true, "self": 0.0004291290001674497, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013769849998652717, "count": 10, "is_parallel": true, "self": 0.0013769849998652717 } } } } } } }, "UnityEnvironment.step": { "total": 317.9157138860128, "count": 27333, "is_parallel": true, "self": 12.210388519029834, "children": { "UnityEnvironment._generate_step_input": { "total": 7.166899932988144, "count": 27333, "is_parallel": true, "self": 7.166899932988144 }, "communicator.exchange": { "total": 255.58238118899658, "count": 27333, "is_parallel": true, "self": 255.58238118899658 }, "steps_from_proto": { "total": 42.956044244998225, "count": 27333, "is_parallel": true, "self": 8.98801760500146, "children": { "_process_rank_one_or_two_observation": { "total": 33.968026639996765, "count": 273330, "is_parallel": true, "self": 33.968026639996765 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.901900001641479e-05, "count": 1, "self": 4.901900001641479e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 602.6588867200212, "count": 506518, "is_parallel": true, "self": 13.163323041010358, "children": { "process_trajectory": { "total": 345.4563586480116, "count": 506518, "is_parallel": true, "self": 344.3220014440117, "children": { "RLTrainer._checkpoint": { "total": 1.1343572039999117, "count": 6, "is_parallel": true, "self": 1.1343572039999117 } } }, "_update_policy": { "total": 244.03920503099926, "count": 136, "is_parallel": true, "self": 65.421015133997, "children": { "TorchPPOOptimizer.update": { "total": 178.61818989700225, "count": 6933, "is_parallel": true, "self": 178.61818989700225 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11588224699994498, "count": 1, "self": 0.0008336149999195186, "children": { "RLTrainer._checkpoint": { "total": 0.11504863200002546, "count": 1, "self": 0.11504863200002546 } } } } } } }