{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8255371451377869, "min": 0.7992426753044128, "max": 2.853862762451172, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7845.9052734375, "min": 7845.9052734375, "max": 29132.23046875, "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": 13.125275611877441, "min": 0.36060476303100586, "max": 13.125275611877441, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2559.4287109375, "min": 69.95732116699219, "max": 2646.312255859375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06711596200008951, "min": 0.06240570015712258, "max": 0.08478555006866587, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26846384800035805, "min": 0.26077973764097573, "max": 0.3728319206600324, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.197517404332757, "min": 0.11600667261062006, "max": 0.27247880428445104, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.790069617331028, "min": 0.46402669044248024, "max": 1.3623940214222552, "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": 26.068181818181817, "min": 3.227272727272727, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 142.0, "max": 1405.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 3.227272727272727, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 142.0, "max": 1405.0, "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": "1759781380", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1759781791" }, "total": 410.33685304200026, "count": 1, "self": 0.4304042750009103, "children": { "run_training.setup": { "total": 0.017473480999797175, "count": 1, "self": 0.017473480999797175 }, "TrainerController.start_learning": { "total": 409.88897528599955, "count": 1, "self": 0.3623691341308586, "children": { "TrainerController._reset_env": { "total": 2.1329174859993145, "count": 1, "self": 2.1329174859993145 }, "TrainerController.advance": { "total": 407.3216814408688, "count": 18192, "self": 0.38225976991361676, "children": { "env_step": { "total": 291.5700932889358, "count": 18192, "self": 254.22405729197726, "children": { "SubprocessEnvManager._take_step": { "total": 37.12242382297245, "count": 18192, "self": 1.173830391926458, "children": { "TorchPolicy.evaluate": { "total": 35.94859343104599, "count": 18192, "self": 35.94859343104599 } } }, "workers": { "total": 0.22361217398611188, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 408.62946740904044, "count": 18192, "is_parallel": true, "self": 183.9446855369988, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002606385000035516, "count": 1, "is_parallel": true, "self": 0.0007224139999379986, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018839710000975174, "count": 10, "is_parallel": true, "self": 0.0018839710000975174 } } }, "UnityEnvironment.step": { "total": 0.05221469200023421, "count": 1, "is_parallel": true, "self": 0.000565761999496317, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004257219998180517, "count": 1, "is_parallel": true, "self": 0.0004257219998180517 }, "communicator.exchange": { "total": 0.04698816500058456, "count": 1, "is_parallel": true, "self": 0.04698816500058456 }, "steps_from_proto": { "total": 0.004235043000335281, "count": 1, "is_parallel": true, "self": 0.0004253699989931192, "children": { "_process_rank_one_or_two_observation": { "total": 0.003809673001342162, "count": 10, "is_parallel": true, "self": 0.003809673001342162 } } } } } } }, "UnityEnvironment.step": { "total": 224.68478187204164, "count": 18191, "is_parallel": true, "self": 10.209760673080382, "children": { "UnityEnvironment._generate_step_input": { "total": 5.797231065012966, "count": 18191, "is_parallel": true, "self": 5.797231065012966 }, "communicator.exchange": { "total": 169.08833119898554, "count": 18191, "is_parallel": true, "self": 169.08833119898554 }, "steps_from_proto": { "total": 39.58945893496275, "count": 18191, "is_parallel": true, "self": 7.274086544801321, "children": { "_process_rank_one_or_two_observation": { "total": 32.31537239016143, "count": 181910, "is_parallel": true, "self": 32.31537239016143 } } } } } } } } } } }, "trainer_advance": { "total": 115.36932838201938, "count": 18192, "self": 0.45501199207410536, "children": { "process_trajectory": { "total": 23.006978446940593, "count": 18192, "self": 22.69668516694128, "children": { "RLTrainer._checkpoint": { "total": 0.3102932799993141, "count": 4, "self": 0.3102932799993141 } } }, "_update_policy": { "total": 91.90733794300468, "count": 90, "self": 39.02191890203267, "children": { "TorchPPOOptimizer.update": { "total": 52.88541904097201, "count": 4587, "self": 52.88541904097201 } } } } } } }, "trainer_threads": { "total": 9.180002962239087e-07, "count": 1, "self": 9.180002962239087e-07 }, "TrainerController._save_models": { "total": 0.07200630700026522, "count": 1, "self": 0.0008755050002946518, "children": { "RLTrainer._checkpoint": { "total": 0.07113080199997057, "count": 1, "self": 0.07113080199997057 } } } } } } }