Designing and deriving effective model-based reinforcement learning (MBRL) algorithms
with a performance improvement guarantee is challenging, mainly attributed to the high …

Learning high-quality $ Q $-value functions plays a key role in the success of many modern
off-policy deep reinforcement learning (RL) algorithms. Previous works primarily focus on …

Dyna-style Model-based reinforcement learning (MBRL) methods have demonstrated
superior sample efficiency compared to their model-free counterparts, largely attributable to …

Off-policy reinforcement learning (RL) has achieved notable success in tackling many
complex real-world tasks, by leveraging previously collected data for policy learning …

In model-based reinforcement learning, the conventional approach to addressing world
model bias is to use gradient optimization methods. However, using a singular policy from …

World models learn the consequences of actions in vision-based interactive systems.
However, in practical scenarios like autonomous driving, noncontrollable dynamics that are …

Offline meta reinforcement learning (OMRL) has emerged as a promising approach for
interaction avoidance and strong generalization performance by leveraging pre-collected …

Training reinforcement learning policies using environment interaction data collected from
varying policies or dynamics presents a fundamental challenge. Existing works often …

Dyna-style model-based reinforcement learning (MBRL) combines model-free agents with
predictive transition models through model-based rollouts. This combination raises a critical …

Animals can navigate through complex environments with amazing flexibility and efficiency:
they forage over large areas, quickly learning rewarding behavior and changing their plans …