While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

Promising results have been achieved recently in category-level manipulation that
generalizes across object instances. Nevertheless, it often requires expensive real-world …

Learning from demonstration (LfD) enables robots to intuitively acquire new skills from
human demonstrations and incrementally evolve robotic intelligence. Given the significance …

With the fast improvement of machine learning, reinforcement learning (RL) has been used
to automate human tasks in different areas. However, training such agents is difficult and …

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 …

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering
can be tedious. However, prior IRL algorithms use on-policy transitions, which require …

Adapting the mastered manipulation skill to novel objects is still challenging for robots.
Recent works have attempted to endow the robot with the ability to adapt to unseen tasks by …

Neural networks have been widely investigated for the control of robot manipulators and
recurrent neural network (RNN) is accepted as a powerful tool for visual servoing. Different …

通过梳理, 总结前人的研究, 首先对深度学**和**化学**的基本理论和算法进行介绍,
进而对深度**化学**的流行算法和在机器人操作领域的应用现状进行综述. 最后 …

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 …