{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9343218803405762, "min": 0.9343218803405762, "max": 2.8745999336242676, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8982.5703125, "min": 8982.5703125, "max": 29438.77734375, "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": 12.804719924926758, "min": 0.36924028396606445, "max": 12.804719924926758, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2496.92041015625, "min": 71.63261413574219, "max": 2596.48193359375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07136903532584397, "min": 0.06478579285447303, "max": 0.0773310431693829, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2854761413033759, "min": 0.2592083976685221, "max": 0.3682154950728028, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1955448988021589, "min": 0.10986061467031273, "max": 0.2784255189638512, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7821795952086356, "min": 0.4394424586812509, "max": 1.392127594819256, "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": 25.15909090909091, "min": 3.1818181818181817, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 140.0, "max": 1395.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.1818181818181817, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 140.0, "max": 1395.0, "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": "1678997759", "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": "1678998287" }, "total": 527.697928565, "count": 1, "self": 0.789583597999922, "children": { "run_training.setup": { "total": 0.11761191499999768, "count": 1, "self": 0.11761191499999768 }, "TrainerController.start_learning": { "total": 526.7907330520001, "count": 1, "self": 0.7063540789973786, "children": { "TrainerController._reset_env": { "total": 9.969570749000013, "count": 1, "self": 9.969570749000013 }, "TrainerController.advance": { "total": 515.9013574700027, "count": 18220, "self": 0.3306190700108118, "children": { "env_step": { "total": 515.5707383999919, "count": 18220, "self": 373.8103299189804, "children": { "SubprocessEnvManager._take_step": { "total": 141.42744472699763, "count": 18220, "self": 2.3613161560069216, "children": { "TorchPolicy.evaluate": { "total": 139.0661285709907, "count": 18220, "self": 139.0661285709907 } } }, "workers": { "total": 0.3329637540138606, "count": 18220, "self": 0.0, "children": { "worker_root": { "total": 524.9481788259922, "count": 18220, "is_parallel": true, "self": 247.20851238598033, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0055158819999974185, "count": 1, "is_parallel": true, "self": 0.003864543000076992, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016513389999204264, "count": 10, "is_parallel": true, "self": 0.0016513389999204264 } } }, "UnityEnvironment.step": { "total": 0.06677307299997892, "count": 1, "is_parallel": true, "self": 0.000621919999957754, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004429079999681562, "count": 1, "is_parallel": true, "self": 0.0004429079999681562 }, "communicator.exchange": { "total": 0.06395021500003395, "count": 1, "is_parallel": true, "self": 0.06395021500003395 }, "steps_from_proto": { "total": 0.0017580300000190618, "count": 1, "is_parallel": true, "self": 0.0003696780000836952, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013883519999353666, "count": 10, "is_parallel": true, "self": 0.0013883519999353666 } } } } } } }, "UnityEnvironment.step": { "total": 277.73966644001183, "count": 18219, "is_parallel": true, "self": 10.893917695007644, "children": { "UnityEnvironment._generate_step_input": { "total": 6.017668401013282, "count": 18219, "is_parallel": true, "self": 6.017668401013282 }, "communicator.exchange": { "total": 225.33146100499943, "count": 18219, "is_parallel": true, "self": 225.33146100499943 }, "steps_from_proto": { "total": 35.49661933899148, "count": 18219, "is_parallel": true, "self": 7.405837949978547, "children": { "_process_rank_one_or_two_observation": { "total": 28.090781389012932, "count": 182190, "is_parallel": true, "self": 28.090781389012932 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014620399997511413, "count": 1, "self": 0.00014620399997511413, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 511.89570426098294, "count": 475556, "is_parallel": true, "self": 12.322287953976456, "children": { "process_trajectory": { "total": 287.45271279100706, "count": 475556, "is_parallel": true, "self": 285.58302830500696, "children": { "RLTrainer._checkpoint": { "total": 1.8696844860000965, "count": 4, "is_parallel": true, "self": 1.8696844860000965 } } }, "_update_policy": { "total": 212.12070351599942, "count": 90, "is_parallel": true, "self": 75.72853386200364, "children": { "TorchPPOOptimizer.update": { "total": 136.39216965399578, "count": 4587, "is_parallel": true, "self": 136.39216965399578 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21330454999997528, "count": 1, "self": 0.0012331240000094112, "children": { "RLTrainer._checkpoint": { "total": 0.21207142599996587, "count": 1, "self": 0.21207142599996587 } } } } } } }