{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8867679834365845, "min": 0.8625775575637817, "max": 2.8458640575408936, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8427.8427734375, "min": 8415.203125, "max": 29050.580078125, "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": 12.476702690124512, "min": 0.35765835642814636, "max": 12.476702690124512, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2432.95703125, "min": 69.3857192993164, "max": 2513.87353515625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.076206760699564, "min": 0.06295228778902788, "max": 0.076206760699564, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.304827042798256, "min": 0.2518091511561115, "max": 0.36391059064115716, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2412176632559767, "min": 0.12177102086727745, "max": 0.312672975191883, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9648706530239068, "min": 0.4870840834691098, "max": 1.563364875959415, "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": 24.15909090909091, "min": 3.3181818181818183, "max": 24.963636363636365, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1063.0, "min": 146.0, "max": 1373.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.15909090909091, "min": 3.3181818181818183, "max": 24.963636363636365, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1063.0, "min": 146.0, "max": 1373.0, "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": "1785842252", "python_version": "3.10.12 (main, Jun 22 2026, 18:55:27) [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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785842586" }, "total": 333.7779420810002, "count": 1, "self": 0.3438514789995679, "children": { "run_training.setup": { "total": 0.02784132899978431, "count": 1, "self": 0.02784132899978431 }, "TrainerController.start_learning": { "total": 333.40624927300087, "count": 1, "self": 0.24856736941001145, "children": { "TrainerController._reset_env": { "total": 2.5206652540000505, "count": 1, "self": 2.5206652540000505 }, "TrainerController.advance": { "total": 330.58960727458907, "count": 18192, "self": 0.2480477874596545, "children": { "env_step": { "total": 245.66404719916318, "count": 18192, "self": 213.78370337152228, "children": { "SubprocessEnvManager._take_step": { "total": 31.725055155919108, "count": 18192, "self": 0.9037224317944492, "children": { "TorchPolicy.evaluate": { "total": 30.82133272412466, "count": 18192, "self": 30.82133272412466 } } }, "workers": { "total": 0.15528867172179162, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 332.4878935218476, "count": 18192, "is_parallel": true, "self": 139.78529438435362, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053007179994892795, "count": 1, "is_parallel": true, "self": 0.0016443719978269655, "children": { "_process_rank_one_or_two_observation": { "total": 0.003656346001662314, "count": 10, "is_parallel": true, "self": 0.003656346001662314 } } }, "UnityEnvironment.step": { "total": 0.032069573000626406, "count": 1, "is_parallel": true, "self": 0.00031127100010053255, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025363199893035926, "count": 1, "is_parallel": true, "self": 0.00025363199893035926 }, "communicator.exchange": { "total": 0.03049647900115815, "count": 1, "is_parallel": true, "self": 0.03049647900115815 }, "steps_from_proto": { "total": 0.001008191000437364, "count": 1, "is_parallel": true, "self": 0.00023261300520971417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007755779952276498, "count": 10, "is_parallel": true, "self": 0.0007755779952276498 } } } } } } }, "UnityEnvironment.step": { "total": 192.70259913749396, "count": 18191, "is_parallel": true, "self": 7.544302703165158, "children": { "UnityEnvironment._generate_step_input": { "total": 4.197699082087638, "count": 18191, "is_parallel": true, "self": 4.197699082087638 }, "communicator.exchange": { "total": 157.57579495858226, "count": 18191, "is_parallel": true, "self": 157.57579495858226 }, "steps_from_proto": { "total": 23.3848023936589, "count": 18191, "is_parallel": true, "self": 4.502286545539391, "children": { "_process_rank_one_or_two_observation": { "total": 18.88251584811951, "count": 181910, "is_parallel": true, "self": 18.88251584811951 } } } } } } } } } } }, "trainer_advance": { "total": 84.67751228796624, "count": 18192, "self": 0.303356560991233, "children": { "process_trajectory": { "total": 16.26002728894673, "count": 18192, "self": 15.99419123694679, "children": { "RLTrainer._checkpoint": { "total": 0.26583605199994054, "count": 4, "self": 0.26583605199994054 } } }, "_update_policy": { "total": 68.11412843802827, "count": 90, "self": 26.187741942158027, "children": { "TorchPPOOptimizer.update": { "total": 41.92638649587025, "count": 4587, "self": 41.92638649587025 } } } } } } }, "trainer_threads": { "total": 7.320013537537307e-07, "count": 1, "self": 7.320013537537307e-07 }, "TrainerController._save_models": { "total": 0.047408643000380835, "count": 1, "self": 0.0009518779988866299, "children": { "RLTrainer._checkpoint": { "total": 0.046456765001494205, "count": 1, "self": 0.046456765001494205 } } } } } } }