{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0162014961242676, "min": 1.0162014961242676, "max": 2.8716814517974854, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9702.6923828125, "min": 9702.6923828125, "max": 29408.890625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.688944816589355, "min": 0.3192116916179657, "max": 12.688944816589355, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2474.34423828125, "min": 61.92707061767578, "max": 2531.3525390625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06807879327642892, "min": 0.06228493224062179, "max": 0.0734991310219972, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2723151731057157, "min": 0.24913972896248715, "max": 0.3650767049361557, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19420241060502388, "min": 0.11265923143318837, "max": 0.28630823142388284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7768096424200955, "min": 0.4506369257327535, "max": 1.4315411571194143, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.318181818181817, "min": 3.409090909090909, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1114.0, "min": 150.0, "max": 1365.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.318181818181817, "min": 3.409090909090909, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1114.0, "min": 150.0, "max": 1365.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679271266", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1679271722" }, "total": 455.81858870099995, "count": 1, "self": 0.4349118029999772, "children": { "run_training.setup": { "total": 0.1050869480000074, "count": 1, "self": 0.1050869480000074 }, "TrainerController.start_learning": { "total": 455.27858994999997, "count": 1, "self": 0.511851550005531, "children": { "TrainerController._reset_env": { "total": 9.672813094000048, "count": 1, "self": 9.672813094000048 }, "TrainerController.advance": { "total": 444.9562978759943, "count": 18200, "self": 0.2799162369969963, "children": { "env_step": { "total": 444.6763816389973, "count": 18200, "self": 323.83985053299284, "children": { "SubprocessEnvManager._take_step": { "total": 120.57506635000084, "count": 18200, "self": 2.175782994002475, "children": { "TorchPolicy.evaluate": { "total": 118.39928335599836, "count": 18200, "self": 118.39928335599836 } } }, "workers": { "total": 0.2614647560036474, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 453.8327030780009, "count": 18200, "is_parallel": true, "self": 217.38164478300052, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005881648000013229, "count": 1, "is_parallel": true, "self": 0.0044609330000184855, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014207149999947433, "count": 10, "is_parallel": true, "self": 0.0014207149999947433 } } }, "UnityEnvironment.step": { "total": 0.06179049499996836, "count": 1, "is_parallel": true, "self": 0.0005575170000611251, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040441699991333735, "count": 1, "is_parallel": true, "self": 0.00040441699991333735 }, "communicator.exchange": { "total": 0.057373972000050344, "count": 1, "is_parallel": true, "self": 0.057373972000050344 }, "steps_from_proto": { "total": 0.003454588999943553, "count": 1, "is_parallel": true, "self": 0.00040327799979422707, "children": { "_process_rank_one_or_two_observation": { "total": 0.003051311000149326, "count": 10, "is_parallel": true, "self": 0.003051311000149326 } } } } } } }, "UnityEnvironment.step": { "total": 236.4510582950004, "count": 18199, "is_parallel": true, "self": 9.217860181990318, "children": { "UnityEnvironment._generate_step_input": { "total": 5.005800175013974, "count": 18199, "is_parallel": true, "self": 5.005800175013974 }, "communicator.exchange": { "total": 192.4317972280046, "count": 18199, "is_parallel": true, "self": 192.4317972280046 }, "steps_from_proto": { "total": 29.795600709991504, "count": 18199, "is_parallel": true, "self": 5.874554227973249, "children": { "_process_rank_one_or_two_observation": { "total": 23.921046482018255, "count": 181990, "is_parallel": true, "self": 23.921046482018255 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014729800000168325, "count": 1, "self": 0.00014729800000168325, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 441.9210897719897, "count": 369579, "is_parallel": true, "self": 9.282247541965717, "children": { "process_trajectory": { "total": 243.75728331502467, "count": 369579, "is_parallel": true, "self": 243.06684714802464, "children": { "RLTrainer._checkpoint": { "total": 0.6904361670000299, "count": 4, "is_parallel": true, "self": 0.6904361670000299 } } }, "_update_policy": { "total": 188.88155891499935, "count": 90, "is_parallel": true, "self": 72.30729178200079, "children": { "TorchPPOOptimizer.update": { "total": 116.57426713299856, "count": 4587, "is_parallel": true, "self": 116.57426713299856 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13748013200006426, "count": 1, "self": 0.0008666270000503573, "children": { "RLTrainer._checkpoint": { "total": 0.1366135050000139, "count": 1, "self": 0.1366135050000139 } } } } } } }