{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8667162656784058, "min": 0.8667162656784058, "max": 2.85058856010437, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8237.271484375, "min": 8237.271484375, "max": 29098.80859375, "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": 12.921371459960938, "min": 0.33551594614982605, "max": 12.921371459960938, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2519.66748046875, "min": 65.09009552001953, "max": 2605.5908203125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06933765144141016, "min": 0.06351135143018374, "max": 0.07422952845974543, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27735060576564063, "min": 0.2586047153887978, "max": 0.3711476422987271, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19150231774969428, "min": 0.12223386118078933, "max": 0.2936645640315963, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7660092709987771, "min": 0.4889354447231573, "max": 1.404561409178902, "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": 25.272727272727273, "min": 3.4318181818181817, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 151.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.4318181818181817, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 151.0, "max": 1400.0, "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": "1743004215", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /kaggle/working/content/ml-agents/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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743004588" }, "total": 372.34482885500006, "count": 1, "self": 0.2713910229999783, "children": { "run_training.setup": { "total": 0.02144187100009276, "count": 1, "self": 0.02144187100009276 }, "TrainerController.start_learning": { "total": 372.051995961, "count": 1, "self": 0.3060223089998999, "children": { "TrainerController._reset_env": { "total": 2.1235057039999674, "count": 1, "self": 2.1235057039999674 }, "TrainerController.advance": { "total": 369.54107361800015, "count": 18192, "self": 0.30952646201160405, "children": { "env_step": { "total": 261.2339372909894, "count": 18192, "self": 196.25138360097662, "children": { "SubprocessEnvManager._take_step": { "total": 64.7960336640042, "count": 18192, "self": 1.114197694010386, "children": { "TorchPolicy.evaluate": { "total": 63.68183596999381, "count": 18192, "self": 63.68183596999381 } } }, "workers": { "total": 0.18652002600856576, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 371.2717601420036, "count": 18192, "is_parallel": true, "self": 198.03160889200342, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023388740000882535, "count": 1, "is_parallel": true, "self": 0.0008227810001244507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015160929999638029, "count": 10, "is_parallel": true, "self": 0.0015160929999638029 } } }, "UnityEnvironment.step": { "total": 0.02592452900000808, "count": 1, "is_parallel": true, "self": 0.00034035900000617403, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003103100000316772, "count": 1, "is_parallel": true, "self": 0.0003103100000316772 }, "communicator.exchange": { "total": 0.024023683999985224, "count": 1, "is_parallel": true, "self": 0.024023683999985224 }, "steps_from_proto": { "total": 0.0012501759999850037, "count": 1, "is_parallel": true, "self": 0.0002488169999423917, "children": { "_process_rank_one_or_two_observation": { "total": 0.001001359000042612, "count": 10, "is_parallel": true, "self": 0.001001359000042612 } } } } } } }, "UnityEnvironment.step": { "total": 173.24015125000017, "count": 18191, "is_parallel": true, "self": 6.867786438996745, "children": { "UnityEnvironment._generate_step_input": { "total": 3.7223433530009515, "count": 18191, "is_parallel": true, "self": 3.7223433530009515 }, "communicator.exchange": { "total": 139.4826255269976, "count": 18191, "is_parallel": true, "self": 139.4826255269976 }, "steps_from_proto": { "total": 23.167395931004876, "count": 18191, "is_parallel": true, "self": 4.369721719031645, "children": { "_process_rank_one_or_two_observation": { "total": 18.79767421197323, "count": 181910, "is_parallel": true, "self": 18.79767421197323 } } } } } } } } } } }, "trainer_advance": { "total": 107.99760986499916, "count": 18192, "self": 0.3646026189995837, "children": { "process_trajectory": { "total": 24.18952412899955, "count": 18192, "self": 23.811835335999604, "children": { "RLTrainer._checkpoint": { "total": 0.3776887929999475, "count": 4, "self": 0.3776887929999475 } } }, "_update_policy": { "total": 83.44348311700003, "count": 90, "self": 32.62340321499926, "children": { "TorchPPOOptimizer.update": { "total": 50.82007990200077, "count": 4587, "self": 50.82007990200077 } } } } } } }, "trainer_threads": { "total": 1.0859998837986495e-06, "count": 1, "self": 1.0859998837986495e-06 }, "TrainerController._save_models": { "total": 0.08139324400008263, "count": 1, "self": 0.0009187080001993309, "children": { "RLTrainer._checkpoint": { "total": 0.0804745359998833, "count": 1, "self": 0.0804745359998833 } } } } } } }