Creating autonomous robots that can actively explore the environment, acquire knowledge
and learn skills continuously is the ultimate achievement envisioned in cognitive and …

In goal-reaching reinforcement learning (RL), the optimal value function has a particular
geometry, called quasimetrics structure. This paper introduces Quasimetric Reinforcement …

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

This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement
learning and sequential decision making, covering value-based RL, policy-gradient …

Representations are at the core of all deep reinforcement learning (RL) methods for both
Markov decision processes (MDPs) and partially observable Markov decision processes …

Extracting a stable and compact representation of the environment is crucial for efficient
reinforcement learning in high-dimensional, noisy, and non-stationary environments …

Visual model-based RL methods typically encode image observations into low-dimensional
representations in a manner that does not eliminate redundant information. This leaves them …

Informational parsimony provides a useful inductive bias for learning representations that
achieve better generalization by being robust to noise and spurious correlations. We …

Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from
relatively little experience and the ability to learn policies that generalize to a range of …

In many sequential decision-making tasks, the agent is not able to model the full complexity
of the world, which consists of multitudes of relevant and irrelevant information. For example …