Reinforcement learning (RL) interacts with the environment to solve sequential decision-
making problems via a trial-and-error approach. Errors are always undesirable in real-world …

Using a high Update-To-Data (UTD) ratio, model-based methods have recently achieved
much higher sample efficiency than previous model-free methods for continuous-action DRL …

Randomized ensembled double Q-learning (REDQ)(Chen et al., 2021b) has recently
achieved state-of-the-art sample efficiency on continuous-action reinforcement learning …

In offline reinforcement learning (offline RL), one of the main challenges is to deal with the
distributional shift between the learning policy and the given dataset. To address this …

We propose VRL3, a powerful data-driven framework with a simple design for solving
challenging visual deep reinforcement learning (DRL) tasks. We analyze a number of major …

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

The Credit Assignment Problem (CAP) refers to the longstanding challenge of
Reinforcement Learning (RL) agents to associate actions with their long-term …

Existing model-based value expansion (MVE) methods typically leverage a world model for
value estimation with a fixed rollout horizon to assist policy learning. However, a proper …

Abstract Model-based reinforcement learning (RL) often achieves higher sample efficiency
in practice than model-free RL by learning a dynamics model to generate samples for policy …

Training large neural networks is known to be time-consuming, with the learning duration
taking days or even weeks. To address this problem, large-batch optimization was …