Objects matter: object-centric world models improve reinforcement learning in visually complex environments
Zhang, Weipu, Jelley, Adam, McInroe, Trevor, Storkey, Amos
–arXiv.org Artificial Intelligence
Deep reinforcement learning has achieved remarkable success in learning control policies from pixels across a wide range of tasks, yet its application remains hindered by low sample efficiency, requiring significantly more environment interactions than humans to reach comparable performance. Model-based reinforcement learning (MBRL) offers a solution by leveraging learnt world models to generate simulated experience, thereby improving sample efficiency. However, in visually complex environments, small or dynamic elements can be critical for decision-making. Yet, traditional MBRL methods in pixel-based environments typically rely on auto-encoding with an $L_2$ loss, which is dominated by large areas and often fails to capture decision-relevant details. To address these limitations, we propose an object-centric MBRL pipeline, which integrates recent advances in computer vision to allow agents to focus on key decision-related elements. Our approach consists of four main steps: (1) annotating key objects related to rewards and goals with segmentation masks, (2) extracting object features using a pre-trained, frozen foundation vision model, (3) incorporating these object features with the raw observations to predict environmental dynamics, and (4) training the policy using imagined trajectories generated by this object-centric world model. Building on the efficient MBRL algorithm STORM, we call this pipeline OC-STORM. We demonstrate OC-STORM's practical value in overcoming the limitations of conventional MBRL approaches on both Atari games and the visually complex game Hollow Knight.
arXiv.org Artificial Intelligence
Jan-27-2025
- Country:
- Asia (0.67)
- Europe (1.00)
- North America > United States
- California
- Los Angeles County > Long Beach (0.14)
- San Diego County (0.14)
- San Francisco County > San Francisco (0.14)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California
- Genre:
- Research Report (1.00)
- Industry:
- Leisure & Entertainment > Games > Computer Games (1.00)
- Technology: