Object-centric World Models For Causality-aware Reinforcement Learning

Abstract

World models have been developed to support sample-efficient deep reinforcement learning agents. However, it remains challenging for world models to accurately replicate environments that are high-dimensional, non-stationary, and composed of multiple objects with rich interactions since most world models learn holistic representations of all environmental components. By contrast, humans perceive the environment by decomposing it into discrete objects, facilitating efficient decision-making. Motivated by this insight, we propose *Slot Transformer Imagination with CAusality-aware reinforcement learning* (STICA), a unified framework in which object-centric Transformers serve as the world model and causality-aware policy and value networks. STICA represents each observation as a set of object-centric tokens, together with tokens for the agent action and the resulting reward, enabling the world model to predict token-level dynamics and interactions. The policy and value networks then estima

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynishimoto2025object

Related papers

• STORM: Efficient Stochastic Transformer Based World Models For Reinforcement Learning (2023)4.52
• Decentralized Transformers With Centralized Aggregation Are Sample-efficient Multi-agent World Models (2024)0.00
• Learning To Play Atari In A World Of Tokens (2024)0.00
• Transformers Are Sample-efficient World Models (2022)0.00
• Recurrent World Models Facilitate Policy Evolution (2018)0.00
• Smaller World Models For Reinforcement Learning (2020)0.00
• Explainable Reinforcement Learning Via A Causal World Model (2023)9.03
• Reinforcement Learning With World Model (2019)0.00