… representations. Furthermore, we prove that our combination of supervised learning (for f) and
reinforcement learning … We present a method that can learn action representations with no …

… contrastive learning and reinforcement learning. CURL trains a visual representation …
jointly trained with the contrastive and reinforcement learning objectives. CURL is a generic …

… We propose a new perspective on representation learning in reinforcement learning based
… Our formulation considers adapting the representation to minimize the (linear) approximation …

… We study how representation learning can accelerate reinforcement learning from rich
observations… Our goal is to learn representations that provide for effective downstream control and …

… of a new class of Reinforcement Learning algorithms, which leverage the … Reinforcement
Learning offers viable solutions to some of the major limitations of current Reinforcement Learn…

… In reinforcement learning, state representations are used to tractably deal with large
problem spaces. State representations serve both to approximate the value function with few …

… experience of the agent – learning a useful representation requires diverse data, while …
with coherent representations. Furthermore, we would like to learn representations that not only …

… representation with a lowdimensional representation of the … learning and also highly prevalent
in reinforcement learning. … a small but rich abstract representation is to allow for improved …

… In value-based reinforcement learning (RL), unlike in supervised learning, the agent faces
… of RL has on representation learning. We demonstrate that a representation that spans the …

… representations learned by deep reinforcement learning systems. Much of the early work on
representations for reinforcement learning … behind deep reinforcement learning methods is …