OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments

Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Sebastian Sztwiertnia, Kristian Kersting

Keywords: Reinforcement learning, environments, benchmark, neurosymbolic, object-centric

TL;DR: OCAtari provides object-centric states from the Atari Learning Environments in a resource efficient way.

Abstract:

Cognitive science and psychology suggest that object-centric representations of complex scenes are a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep reinforcement learning approaches only rely on pixel-based representations that do not capture the compositional properties of natural scenes.
For this, we need environments and datasets that allow us to work and evaluate object-centric approaches.
In our work, we extend the Atari Learning Environments, the most-used evaluation framework for deep RL approaches, by introducing OCAtari, that performs resource-efficient extractions of the object-centric states for these games. Our framework allows for object discovery, object representation learning, as well as object-centric RL.
We evaluate OCAtari's detection capabilities and resource efficiency.

Submission Number: 46