{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.826098620891571, "min": 0.8126764297485352, "max": 2.824427366256714, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7851.2412109375, "min": 7851.2412109375, "max": 28831.75390625, "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": 12.582376480102539, "min": 0.48819032311439514, "max": 12.582376480102539, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2453.5634765625, "min": 94.70892333984375, "max": 2533.924072265625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06378324597108967, "min": 0.06244859063693131, "max": 0.07756350716215321, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2551329838843587, "min": 0.24979436254772525, "max": 0.38781753581076606, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2308611206564249, "min": 0.12067603477158165, "max": 0.28300833678713033, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9234444826256996, "min": 0.4827041390863266, "max": 1.4150416839356517, "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": 25.113636363636363, "min": 3.5681818181818183, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 157.0, "max": 1350.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 3.5681818181818183, "max": 25.113636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 157.0, "max": 1350.0, "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": "1756135112", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/home/ubuntu/.local/bin/mlagents-learn /home/ubuntu/SnowballTarget.yaml --env=/home/ubuntu/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756135291" }, "total": 178.460064676, "count": 1, "self": 0.16754495400004998, "children": { "run_training.setup": { "total": 0.015393196999866632, "count": 1, "self": 0.015393196999866632 }, "TrainerController.start_learning": { "total": 178.27712652500009, "count": 1, "self": 0.16338612000527064, "children": { "TrainerController._reset_env": { "total": 2.2115766210001766, "count": 1, "self": 2.2115766210001766 }, "TrainerController.advance": { "total": 175.86167315399462, "count": 18192, "self": 0.15642901998239722, "children": { "env_step": { "total": 121.06598562700515, "count": 18192, "self": 92.74650041203199, "children": { "SubprocessEnvManager._take_step": { "total": 28.2102453139737, "count": 18192, "self": 0.5664078529575818, "children": { "TorchPolicy.evaluate": { "total": 27.64383746101612, "count": 18192, "self": 27.64383746101612 } } }, "workers": { "total": 0.10923990099945513, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 177.84109907204333, "count": 18192, "is_parallel": true, "self": 98.02367565004465, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001077398000006724, "count": 1, "is_parallel": true, "self": 0.00032212199994319235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007552760000635317, "count": 10, "is_parallel": true, "self": 0.0007552760000635317 } } }, "UnityEnvironment.step": { "total": 0.014810322000130327, "count": 1, "is_parallel": true, "self": 0.00030146100039019075, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023475199986933148, "count": 1, "is_parallel": true, "self": 0.00023475199986933148 }, "communicator.exchange": { "total": 0.013401651999856767, "count": 1, "is_parallel": true, "self": 0.013401651999856767 }, "steps_from_proto": { "total": 0.0008724570000140375, "count": 1, "is_parallel": true, "self": 0.0001789620000636205, "children": { "_process_rank_one_or_two_observation": { "total": 0.000693494999950417, "count": 10, "is_parallel": true, "self": 0.000693494999950417 } } } } } } }, "UnityEnvironment.step": { "total": 79.81742342199868, "count": 18191, "is_parallel": true, "self": 3.090445016023068, "children": { "UnityEnvironment._generate_step_input": { "total": 1.694828090992587, "count": 18191, "is_parallel": true, "self": 1.694828090992587 }, "communicator.exchange": { "total": 65.65267341698473, "count": 18191, "is_parallel": true, "self": 65.65267341698473 }, "steps_from_proto": { "total": 9.379476897998302, "count": 18191, "is_parallel": true, "self": 1.7557194689513835, "children": { "_process_rank_one_or_two_observation": { "total": 7.623757429046918, "count": 181910, "is_parallel": true, "self": 7.623757429046918 } } } } } } } } } } }, "trainer_advance": { "total": 54.63925850700707, "count": 18192, "self": 0.20531113300239667, "children": { "process_trajectory": { "total": 12.296997453003996, "count": 18192, "self": 12.076752963003628, "children": { "RLTrainer._checkpoint": { "total": 0.2202444900003684, "count": 4, "self": 0.2202444900003684 } } }, "_update_policy": { "total": 42.13694992100068, "count": 90, "self": 18.915861567998945, "children": { "TorchPPOOptimizer.update": { "total": 23.221088353001733, "count": 4587, "self": 23.221088353001733 } } } } } } }, "trainer_threads": { "total": 5.80000005356851e-07, "count": 1, "self": 5.80000005356851e-07 }, "TrainerController._save_models": { "total": 0.04049005000001671, "count": 1, "self": 0.000662395000063043, "children": { "RLTrainer._checkpoint": { "total": 0.039827654999953666, "count": 1, "self": 0.039827654999953666 } } } } } } }