Reinforcement learning (RL) allows an agent to solve sequential decision-making problems
by interacting with an environment in a trial-and-error fashion. When these environments are …

In recent years, the research on reinforcement learning (RL) has focused on function
approximation in learning prediction and control of Markov decision processes (MDPs). The …

Abstract Representation learning and option discovery are two of the biggest challenges in
reinforcement learning (RL). Proto-value functions (PVFs) are a well-known approach for …

Exploration is an essential component of reinforcement learning algorithms, where agents
need to learn how to predict and control unknown and often stochastic environments …

We study the learning dynamics of self-predictive learning for reinforcement learning, a
family of algorithms that learn representations by minimizing the prediction error of their own …

We describe the Fourier basis, a linear value function approximation scheme based on the
Fourier series. We empirically demonstrate that it performs well compared to radial basis …

Options in reinforcement learning allow agents to hierarchically decompose a task into
subtasks, having the potential to speed up learning and planning. However, autonomously …

Reasoning at multiple levels of temporal abstraction is one of the key attributes of
intelligence. In reinforcement learning, this is often modeled through temporally extended …

This paper introduces a novel spectral framework for solving Markov decision processes
(MDPs) by jointly learning representations and optimal policies. The major components of …

In this paper we introduce a novel approach to manifold alignment, based on Procrustes
analysis. Our approach differs from" semi-supervised alignment" in that it results in a …