An agent that is capable of predicting what happens next can perform a variety of tasks
through planning with no additional training. Furthermore, such an agent can internally …

People navigating in unfamiliar buildings take advantage of myriad visual, spatial and
semantic cues to efficiently achieve their navigation goals. Towards equipping …

Anchor-bolt insertion is a peg-in-hole task performed in the construction field for holes in
concrete. Efforts have been made to automate this task, but the variable lighting and hole …

Model-based reinforcement learning (MBRL) has gained much attention for its ability to
learn complex behaviors in a sample-efficient way: planning actions by generating …

This paper presents replay overshooting (RO), an algorithm that uses properties of the
extended Kalman filter (EKF) to learn nonlinear stochastic latent dynamics models suitable …

基于视频数据的深度预测学习(以下简称“深度预测学习”) 属于深度学习, 计算机视觉和强化学习
的交叉融合研究方向, 是气象预报, 自动驾驶, 机器人视觉控制等场景下智能预测与决策系统的 …

State-of-the-art world models such as DreamerV2 have significantly improved the
capabilities of model-based reinforcement learning. However, these approaches typically …

Abstract Model-based reinforcement learning (MBRL) has often been touted for its potential
to improve on the sample-efficiency, generalization, and safety of existing reinforcement …

The previous chapters discussed model-free methods, and we saw their success in video
games and simulated robotics. In model-free methods, the agent updates a policy directly …

Abstract Deep Reinforcement Learning (DRL) is a rapidly growing area of research in the
field of artificial intelligence, which has shown exceptional success in solving complex tasks …