> For the complete documentation index, see [llms.txt](https://docs.zerve.ai/zerve-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zerve.ai/zerve-docs/superagents/batches/exploration.md). # Exploration Try competing approaches scored on the same number, and keep the best. An **Exploration** batch tries several competing approaches to the same problem, scores each on the same number, and keeps the winner. ## When it's used Use Exploration when there are several plausible ways to do something and a clear number to judge them by. For example: * Comparing three volatility forecasting methods on out-of-sample error * Testing several feature sets for a credit risk model on validation accuracy * Trying different ways to clean a dataset, scored on downstream model performance ## How it works 1. The superagent defines the approaches to try and the score that decides between them, including whether higher or lower is better. 2. Each approach is built by its own worker, in parallel. 3. Each is scored on the same number. 4. The best-scoring approach wins. Its worker takes over the role on the team, and the other workers are retired. They show on the Map as **replaced**. An exploration can be stopped early once one approach is clearly ahead, to save budget. ## What you see The batch's results view is a **score chart** comparing the approaches. ## Example request > Try three approaches to forecasting next-day volatility, a GARCH model, a realized-volatility model and a gradient-boosted model, and keep whichever has the lowest out-of-sample error. If the approaches can't be compared on a single number, use a [Tournament](/zerve-docs/superagents/batches/tournament.md) instead. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.zerve.ai/zerve-docs/superagents/batches/exploration.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.