{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9223536252975464, "min": 0.9134339094161987, "max": 2.8575165271759033, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8766.048828125, "min": 8766.048828125, "max": 29169.529296875, "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": 12.039687156677246, "min": 0.3422595262527466, "max": 12.039687156677246, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2347.739013671875, "min": 66.39834594726562, "max": 2442.177734375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0673827538943014, "min": 0.06102887743715353, "max": 0.07493763099474189, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2695310155772056, "min": 0.25178067562599465, "max": 0.36941626134520283, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17782365925171795, "min": 0.12017838958212557, "max": 0.3211473984753384, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7112946370068718, "min": 0.48071355832850227, "max": 1.410268900149009, "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.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.Environment.CumulativeReward.mean": { "value": 23.704545454545453, "min": 3.522727272727273, "max": 23.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1043.0, "min": 155.0, "max": 1296.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.704545454545453, "min": 3.522727272727273, "max": 23.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1043.0, "min": 155.0, "max": 1296.0, "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": "1751566806", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751567225" }, "total": 419.839667692, "count": 1, "self": 0.48815126400000963, "children": { "run_training.setup": { "total": 0.023557428999993135, "count": 1, "self": 0.023557428999993135 }, "TrainerController.start_learning": { "total": 419.327958999, "count": 1, "self": 0.3814333940069332, "children": { "TrainerController._reset_env": { "total": 3.713517696999986, "count": 1, "self": 3.713517696999986 }, "TrainerController.advance": { "total": 415.154591347993, "count": 18192, "self": 0.38190915299475137, "children": { "env_step": { "total": 296.0844239580037, "count": 18192, "self": 228.17382154000393, "children": { "SubprocessEnvManager._take_step": { "total": 67.69209812900527, "count": 18192, "self": 1.2173474260119974, "children": { "TorchPolicy.evaluate": { "total": 66.47475070299328, "count": 18192, "self": 66.47475070299328 } } }, "workers": { "total": 0.21850428899449525, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 417.870322339991, "count": 18192, "is_parallel": true, "self": 217.9484787810067, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005059909999999945, "count": 1, "is_parallel": true, "self": 0.00372425900008011, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013356509999198352, "count": 10, "is_parallel": true, "self": 0.0013356509999198352 } } }, "UnityEnvironment.step": { "total": 0.0359409320000168, "count": 1, "is_parallel": true, "self": 0.000566473000105816, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003899650000107613, "count": 1, "is_parallel": true, "self": 0.0003899650000107613 }, "communicator.exchange": { "total": 0.03320631699995147, "count": 1, "is_parallel": true, "self": 0.03320631699995147 }, "steps_from_proto": { "total": 0.0017781769999487551, "count": 1, "is_parallel": true, "self": 0.0003435909999325304, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014345860000162247, "count": 10, "is_parallel": true, "self": 0.0014345860000162247 } } } } } } }, "UnityEnvironment.step": { "total": 199.92184355898428, "count": 18191, "is_parallel": true, "self": 9.523343581989081, "children": { "UnityEnvironment._generate_step_input": { "total": 5.167670399997576, "count": 18191, "is_parallel": true, "self": 5.167670399997576 }, "communicator.exchange": { "total": 155.13422655800105, "count": 18191, "is_parallel": true, "self": 155.13422655800105 }, "steps_from_proto": { "total": 30.096603018996575, "count": 18191, "is_parallel": true, "self": 5.455435112003954, "children": { "_process_rank_one_or_two_observation": { "total": 24.64116790699262, "count": 181910, "is_parallel": true, "self": 24.64116790699262 } } } } } } } } } } }, "trainer_advance": { "total": 118.68825823699456, "count": 18192, "self": 0.4830806229896325, "children": { "process_trajectory": { "total": 25.760548625003935, "count": 18192, "self": 25.373613233003994, "children": { "RLTrainer._checkpoint": { "total": 0.3869353919999412, "count": 4, "self": 0.3869353919999412 } } }, "_update_policy": { "total": 92.44462898900099, "count": 90, "self": 37.99018648500282, "children": { "TorchPPOOptimizer.update": { "total": 54.454442503998166, "count": 4587, "self": 54.454442503998166 } } } } } } }, "trainer_threads": { "total": 8.250000291809556e-07, "count": 1, "self": 8.250000291809556e-07 }, "TrainerController._save_models": { "total": 0.07841573500002141, "count": 1, "self": 0.0007912700000360928, "children": { "RLTrainer._checkpoint": { "total": 0.07762446499998532, "count": 1, "self": 0.07762446499998532 } } } } } } }