.. _quick-start-chapter: =========== Quick Start =========== This page reproduces the small Gaussian test case used to verify the simulator. 1. Open Argonaut ================ Open the simulator URL in a browser: `https://argonautsim-382548405389.us-central1.run.app/ `_ 2. Select a Dataset =================== In the Dataset panel, select ``Gaussian [Subset]``. Argonaut loads the built-in dataset and shows the Agent Selection panel. The tested deployment reported 11 available Gaussian subset agents. 3. Select Agents, Plans, and Dimensions ======================================= Use the following values: .. list-table:: :header-rows: 1 :widths: 30 20 50 * - Setting - Value - Action * - Number of agents (N) - ``3`` - Keep the default value and click ``Done (Lock Selection)``. * - Plans per agent (M) - ``2`` - Change the plan count to ``2`` and click ``Done (Lock Selection)``. * - Number of dimensions (D) - ``100`` - Change the dimension count to ``100`` and click ``Done (Lock Selection)``. The Plan Editor then shows the selected agents and the first 10 plan dimensions. 4. Configure the Algorithm ========================== For the tested run, use: .. list-table:: :header-rows: 1 :widths: 35 65 * - Setting - Value * - Algorithm - ``Tree-Based Iterative``, ``Brute Force Exhaustive search``, or ``Both Tree-Based + Brute Force`` * - Iterations - ``40`` * - Children per node - ``2`` * - Simulations - ``1`` * - Global cost - ``VAR - Variance`` * - Local cost - ``INDEX - Plan index`` * - Objective weights - :math:`\alpha=0`, :math:`\beta=0` 5. Run ====== Click ``Run Algorithm``. When the run completes, Argonaut shows: * A completion banner. * Final metrics for the selected algorithm. * ``Downloads`` and ``Logs`` tabs. * ``Open Visualizer``. .. note:: You can kill the Run at any time, then the simulator will output partial results.