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

World models are a fundamental component in model-based reinforcement learning
(MBRL). To perform temporally extended and consistent simulations of the future in partially …

Existing approaches for improving generalization in deep reinforcement learning (RL) have
mostly focused on representation learning, neglecting RL-specific aspects such as …

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

The ability to separate signal from noise, and reason with clean abstractions, is critical to
intelligence. With this ability, humans can efficiently perform real world tasks without …

Abstract Reconstruction-based Model-Based Reinforcement Learning (MBRL) agents, such
as Dreamer, often fail to discard task-irrelevant visual distractions that are prevalent in …

Deep reinforcement learning policies, despite their outstanding efficiency in simulated visual
control tasks, have shown disappointing ability to generalize across disturbances in the …

In recent years, domains such as natural language processing and image recognition have
popularized the paradigm of using large datasets to pretrain representations that can be …

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

Learning dynamics models accurately is an important goal for Model-Based Reinforcement
Learning (MBRL), but most MBRL methods learn a dense dynamics model which is …