Gaussian processes (GPs) provide a framework for Bayesian inference that can offer
principled uncertainty estimates for a large range of problems. For example, if we consider …

We establish a new connection between value and policy based reinforcement learning
(RL) based on a relationship between softmax temporal value consistency and policy …

We propose a general framework for entropy-regularized average-reward reinforcement
learning in Markov decision processes (MDPs). Our approach is based on extending the …

Abstract Deep Reinforcement Learning (DRL), which can learn complex policies with high-
dimensional observations as inputs, eg, images, has been successfully applied to various …

We present a reformulation of the stochastic optimal control problem in terms of KL
divergence minimisation, not only providing a unifying perspective of previous approaches …

Policy optimization methods are popular reinforcement learning (RL) algorithms, because
their incremental and on-policy nature makes them more stable than the value-based …

Trust region methods, such as TRPO, are often used to stabilize policy optimization
algorithms in reinforcement learning (RL). While current trust region strategies are effective …

This paper explores a reinforcement learning (RL) approach that designs automatic control
strategies in a large-scale chemical process control scenario as the first step for leveraging …

Abstract Generative Adversarial Imitation Learning (GAIL) can learn policies without
explicitly defining the reward function from demonstrations. GAIL has the potential to learn …

Empowerment is an information-theoretic method that can be used to intrinsically motivate
learning agents. It attempts to maximize an agent's control over the environment by …