Abstract Model-based reinforcement learning is a promising direction to improve the sample
efficiency of reinforcement learning with learning a model of the environment. Previous …

Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient,
adaptive, and explainable by learning an explicit model of the environment. While the …

Abstract Stochastic Value Gradient (SVG) methods underlie many recent achievements of
model-based Reinforcement Learning agents in continuous state-action spaces. Despite …

Reinforcement learning (RL) is mechanized to learn from experience. It solves the problem
in sequential decisions by optimizing reward-punishment through experimentation of the …

Abstract Model-based Reinforcement Learning (MBRL) agents use data collected by
exploration of the environment to produce a model of the dynamics, which is then used to …

We investigate the generalization performance of predictive models in model-based
reinforcement learning when trained using maximum likelihood estimation (MLE) versus …