1K+
Downloads
Everyone
info
About this game
In ArtBot players of all ages learn the basics of Artificial Intelligence. Your quest is to find and retrieve stolen art objects. You train your AI helper to recognise and locate the objects hidden in a maze of dungeons, and see how supervised and reinforcement learning works.
Our aim is to introduce players, through ArtBot, to core principles and concepts of Artificial Intelligence. Players have the quest to find and retrieve valuable art objects that have been stolen and hidden. Through the first part of the game, the process of supervised learning is introduced; players train their AI helper to recognise specific art objects (i.e. paintings and sculptures). They classify a set of training data, experiment with different parameters, and then see how well the helper was trained by observing how it classifies a set of testing data. This is where the players teach their helper to recognise which objects they are looking for, for their quest.
During the second part of the game, the players and their AI helper need to navigate through a series of dungeons, locate, and collect the stolen art objects. In this part, the players are introduced to the processes of reinforcement learning; they guide their helper by indicating what type of objects to look for and which ones to avoid (e.g. traps), by assigning rewards to the right objects. The AI helper tries to find its path based on the parameters set by the players, such as the exploration and exploitation rates. The players watch the process, they can pause or accelerate it, and think what the optimal settings would be for helping the AI find as many objects as possible.
The game was designed by a team of educators, game developers, and AI experts with the aim to support AI literacy of primary and secondary education students. Beyond the technical aspects of AI, our goal was to trigger the critical thinking of players on the aspects, factors and bias that may shape the architecture and behaviour of AI agents and systems. The game guides the player through a set of actions, but also provides opportunities for exploration, experimentation, and reflection; players are encouraged to construct their knowledge by observing the outcomes of their actions, evaluate the results, make and test their hypotheses.
Through the design of the game we tried to avoid common stereotypes and address students’ misconceptions of AI, such as the anthropomorphic nature of AI systems - the AI helper is an unidentified artifact rather than a robot. Players, though, do have the option to choose and modify their own avatar for the AI helper. By setting the game in the context of cultural heritage (art objects) our aim was to address the application of AI systems in multiple different areas, beyond computing and programming, such as archaeology, art, and transportation.
Our aim is to introduce players, through ArtBot, to core principles and concepts of Artificial Intelligence. Players have the quest to find and retrieve valuable art objects that have been stolen and hidden. Through the first part of the game, the process of supervised learning is introduced; players train their AI helper to recognise specific art objects (i.e. paintings and sculptures). They classify a set of training data, experiment with different parameters, and then see how well the helper was trained by observing how it classifies a set of testing data. This is where the players teach their helper to recognise which objects they are looking for, for their quest.
During the second part of the game, the players and their AI helper need to navigate through a series of dungeons, locate, and collect the stolen art objects. In this part, the players are introduced to the processes of reinforcement learning; they guide their helper by indicating what type of objects to look for and which ones to avoid (e.g. traps), by assigning rewards to the right objects. The AI helper tries to find its path based on the parameters set by the players, such as the exploration and exploitation rates. The players watch the process, they can pause or accelerate it, and think what the optimal settings would be for helping the AI find as many objects as possible.
The game was designed by a team of educators, game developers, and AI experts with the aim to support AI literacy of primary and secondary education students. Beyond the technical aspects of AI, our goal was to trigger the critical thinking of players on the aspects, factors and bias that may shape the architecture and behaviour of AI agents and systems. The game guides the player through a set of actions, but also provides opportunities for exploration, experimentation, and reflection; players are encouraged to construct their knowledge by observing the outcomes of their actions, evaluate the results, make and test their hypotheses.
Through the design of the game we tried to avoid common stereotypes and address students’ misconceptions of AI, such as the anthropomorphic nature of AI systems - the AI helper is an unidentified artifact rather than a robot. Players, though, do have the option to choose and modify their own avatar for the AI helper. By setting the game in the context of cultural heritage (art objects) our aim was to address the application of AI systems in multiple different areas, beyond computing and programming, such as archaeology, art, and transportation.
Updated on
Safety starts with understanding how developers collect and share your data. Data privacy and security practices may vary based on your use, region, and age. The developer provided this information and may update it over time.
No data shared with third parties
Learn more about how developers declare sharing
No data collected
Learn more about how developers declare collection
What's new
Engine update and bug fixes.