> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fincept.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Aversion tuning

> Tune an optimisation policy's risk, trade and holding aversions by back-testing: a grid of values side by side (risk-return frontier of realized results) or a greedy search that keeps moving the values while Sharpe ratio, return or growth improves.

Toolset `mpo_tuning`: 2 tools.

| Tool | What it does | Notes |
| - | - | - |
| `mpo_gamma_sweep` | Back-tests the same optimisation policy for every combination (at most 24) of the given risk, trade and holding aversions, over the same window and costs. | |
| `mpo_hyperparameter_search` | Searches the risk, trade and/or holding aversions that maximise a back-test metric (Sharpe by default) with the simulator's greedy method: from the objective's values it back-tests one move up and down for each tuned aversion, takes the best while the metric improves and stops when no move does. | |

Inputs, limits and outputs are described in [Fincept Multi-Period](/guides/fincept-multi-period). Full schemas: `fincept_describe_tool`.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.