Unsupervised video-based object-centric learning is a promising avenue to learn structured
representations from large, unlabeled video collections, but previous approaches have only …

Manipulating objects is a hallmark of human intelligence, and an important task in domains
such as robotics. In principle, Reinforcement Learning (RL) offers a general approach to …

In Model-Based Reinforcement Learning (MBRL), incorporating causal structures into
dynamics models provides agents with a structured understanding of the environments …

Current Reinforcement Learning (RL) methods often suffer from sample-inefficiency,
resulting from blind exploration strategies that neglect causal relationships among states …

Causal dynamics learning has recently emerged as a promising approach to enhancing
robustness in reinforcement learning (RL). Typically, the goal is to build a dynamics model …

Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable
skills through autonomous, reward-free environment interaction. Existing unsupervised skill …

Offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing
pre-collected datasets to learn models and policies, especially in scenarios where …

The ability to autonomously understand complex environments and act in them is an
essential goal in artificial agents' development. State-of-the-art agents may excel in …

Deep Reinforcement Learning (DRL) has struggled with pixel-based controlling tasks that
have numerous entities, long sequences, and logical dependencies. Methods using …