The reinforcement learning (RL) research area is very active, with an important number of
new contributions, especially considering the emergent field of deep RL (DRL). However, a …

We present BYOL-Explore, a conceptually simple yet general approach for curiosity-driven
exploration in visually complex environments. BYOL-Explore learns the world …

Convex Reinforcement Learning (RL) is a recently introduced framework that generalizes
the standard RL objective to any convex (or concave) function of the state distribution …

Animals have a developed ability to explore that aids them in important tasks such as
locating food, exploring for shelter, and finding misplaced items. These exploration skills …

A promising technique for exploration is to maximize the entropy of visited state distribution,
ie, state entropy, by encouraging uniform coverage of visited state space. While it has been …

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural
Networks (DNNs) for function approximation, has demonstrated considerable success in …

In the absence of assigned tasks, a learning agent typically seeks to explore its environment
efficiently. However, the pursuit of exploration will bring more safety risks. An under-explored …

In the maximum state entropy exploration framework, an agent interacts with a reward-free
environment to learn a policy that maximizes the entropy of the expected state visitations it is …

Abstract The classic Reinforcement Learning (RL) formulation concerns the maximization of
a scalar reward function. More recently, convex RL has been introduced to extend the RL …

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 …