OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments

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

Reinforcement Learning Journal, vol. 1, 2024, pp. 400–449.

Presented at the Reinforcement Learning Conference (RLC), Amherst Massachusetts, August 9–12, 2024.


Download:

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.


Citation Information:

Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Sebastian Sztwiertnia, and Kristian Kersting. "OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments." Reinforcement Learning Journal, vol. 1, 2024, pp. 400–449.

BibTeX:

@article{delfosse2024ocatari,
    title={{OCAtari}: {O}bject-Centric {Atari} 2600 Reinforcement Learning Environments},
    author={Delfosse, Quentin and Bl{\"{u}}ml, Jannis and Gregori, Bjarne and Sztwiertnia, Sebastian and Kersting, Kristian},
    journal={Reinforcement Learning Journal},
    volume={1},
    pages={400--449},
    year={2024}
}