One of the key capabilities of intelligent agents is the ability to discover useful skills without
external supervision. However, the current unsupervised skill discovery methods are often …

Unsupervised pre-training strategies have proven to be highly effective in natural language
processing and computer vision. Likewise, unsupervised reinforcement learning (RL) holds …

In the field of unsupervised skill discovery (USD), a major challenge is limited exploration,
primarily due to substantial penalties when skills deviate from their initial trajectories. To …

Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural
policies to solve complex control tasks. However, these policies tend to be overfit to the …

Dropped into an unknown environment, what should an agent do to quickly learn about the
environment and how to accomplish diverse tasks within it? We address this question within …

Being able to discover diverse useful skills without external reward functions is beneficial in
reinforcement learning research. Previous unsupervised skill discovery approaches mainly …

The past few years have seen rapid progress in combining reinforcement learning (RL) with
deep learning. Various breakthroughs ranging from games to robotics have spurred the …

Learning rich skills under the option framework without supervision of external rewards is at
the frontier of reinforcement learning research. Existing works mainly fall into two distinctive …

In reinforcement learning, the graph Laplacian has proved to be a valuable tool in the task-
agnostic setting, with applications ranging from skill discovery to reward shaping. Recently …

This paper addresses the challenges of deploying reinforcement learning (RL) models for
traffic signal control (TSC) in real-world environments. Real-world training can prevent …