This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement
learning and sequential decision making, covering value-based RL, policy-gradient …

Reinforcement learning (RL) is a promising approach for solving robotic manipulation tasks.
However, it is challenging to apply the RL algorithms directly in the real world. For one thing …

Recently, people have shown that large-scale pre-training from diverse internet-scale data is
the key to building a generalist model, as witnessed in the natural language processing …

Reinforcement learning (RL) promises a framework for near-universal problem-solving. In
practice however, RL algorithms are often tailored to specific benchmarks, relying on …

Sample efficiency in Reinforcement Learning (RL) has traditionally been driven by
algorithmic enhancements. In this work, we demonstrate that scaling can also lead to …

A significant aspiration of offline reinforcement learning (RL) is to develop a generalist agent
with high capabilities from large and heterogeneous datasets. However, prior approaches …

Recently, Model-based Reinforcement Learning (MBRL) methods have demonstrated
stunning sample efficiency in various RL domains. However, achieving this extraordinary …

Over the last decade, there have been significant advances in model-based deep
reinforcement learning. One of the most successful such algorithms is AlphaZero which …