> For the complete documentation index, see [llms.txt](https://docs.buildings.ability.abb/collection/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.buildings.ability.abb/collection/extras/innovation-hub-game/overview.md).

# Overview

Understand the goal, setup, and scoring of the Innovation Hub Game.

The Innovation Hub Game is a simplified heating and cooling control game.

It simulates two identical rooms under the same outside conditions.

One room is controlled by the AI.

The other room is controlled by rule-based control.

As soon as you choose an action, you take over that room.

## Goal

Your goal is to outperform the AI.

To do that, balance two objectives:

* Keep the indoor temperature in the grey comfort zone.
* Keep energy cost as low as possible.

The comfort zone is **19°C to 24°C**.

Comfort only matters while people are in the room.

When the room is empty, energy optimization matters more.

## The Two Rooms

The two rooms start from the same initial state.

They also see the same outside temperature, occupancy, and energy tariff.

This makes the comparison fair.

The difference comes from the control strategy.

* **AI room:** controlled by the AI.
* **Player room:** controlled by rule-based control until you take over.

## Actions You Can Take

You can choose one of three actions:

* **Heating**
* **Cooling**
* **Do Nothing**

Only one action can be active at a time.

Turning one on automatically turns the others off.

As soon as you activate one action, the game starts.

If you switch all actions off, control returns to rule-based control.

## Time and Pace

The simulation runs in **15-minute steps**.

The pace setting defines how much real time passes before the next simulated step starts.

Example:

* **1 sec** means **1 second real time = 15 minutes simulated time**.
* **10 sec** means **10 seconds real time = 15 minutes simulated time**.

## Stopping the Game

You can stop your own control in two ways:

* switch all actions off
* activate **Stop the Game**

Both hand control back to rule-based control.

The game has a minimum duration of **24 simulated hours**.

If you stop before that, rule-based control continues until the minimum duration is reached.

The game can also continue beyond 24 hours.

## Score and Performance

Your result is shown as a percentage.

**100%** means your performance matches the AI.

A value above **100%** means you beat the AI.

A value below **100%** means the AI performed better.

The score does not go below **0%**.

The exact reward formula is not important for normal gameplay.

Focus on comfort during occupancy and low energy cost over time.

## What to Watch on the Screen

### Highscore and Time

* **Today's Highscore:** best performance reached today.
* **Day of Week:** current simulated weekday.
* **Time of Day:** current simulated time.
* **Minimum game length remaining:** time left until the minimum run time is complete.

### Game State and Actions

* **Game State:** shows whether the game is running.
* **Your Final Score:** your current result compared with the AI.
* **Rule/Player Action:** current action in your room.
* **AI Action:** current action in the AI room.

### User Control

* **Heating:** forces heating in your room.
* **Cooling:** forces cooling in your room.
* **Do Nothing:** leaves the room without active heating or cooling.
* **Stop the Game:** ends your control and hands the room back to rule-based control.

### Environment Observations

* **People in Office:** current occupancy.
* **Outdoor Temperature:** current outside temperature.
* **Energy Tariff:** current energy price.

### Charts

* **You vs AI Energy Cost:** compares energy cost over time.
* **You vs AI Temperature:** compares indoor temperature over time.
* **You vs AI Comfort:** compares comfort performance over time.
* **Your Current Performance:** shows how your current run compares with the AI.


---

# 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.buildings.ability.abb/collection/extras/innovation-hub-game/overview.md?ask=<question>&goal=<user_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.
