In situations where a task can be cleanly formulated and data is plentiful, modern machine learning (ML) techniques have achieved impressive (and often super-human) results. Here, "plentiful data" can mean labels from humans, access to a simulator and well designed reward function, or other forms of interaction and supervision.
On the other hand, in situations where tasks cannot be cleanly formulated and plentifully supervised, ML has not yet shown the same progress, we still seem far from flexible agents that can learn without human engineers carefully designing or collating their supervision. This is problematic in many settings where machine learning is or will be applied in real world settings, where these agents have to interact with human users and may be used in settings that go beyond any initial clean training data used during system development. A key open question is how to make machine learning effective and robust enough to operate in real world open domains.
Artificial open worlds are ideal laboratories for studying how to extend the successes of ML to build such agents.
Open worlds are characterized by:
Large (or infinite) collections of tasks, often not specified until test time; or lack of well defined tasks altogether (despite there being lots to do).
"Unbounded" environments, long "episodes"; or no episodes at all.
Many interacting agents; more generally, emergent behavior from interactions with the environment.
On one hand, they retain many of the challenging features of the real world with respect to studying learning agents. On the other hand, they allow cheap collection of environment interaction data. Furthermore, because many artificial worlds of interest are games that people enjoy playing, they could allow interaction with humans at scale.
The aim of the workshop is to catalyze research towards addressing these challenges posed by machine learning in open worlds. Our goal is to bring together researchers with a wide range of perspectives whose work focuses on, or is enabled by, open worlds. We want to foster ideas and discussions around the specific challenges that arise when targeting machine learning applications in open worlds. This workshop will be an exciting opportunity to reflect on the specific limitations of today's machine learning approaches that need to be overcome in order to broaden open world domains, and to generate discussions and ideas that could drive research in this space for years to come.