Towards a Simple Approach to Multi-step Model-based Reinforcement Learning
arXiv: Learning, Volume abs/1811.00128, 2018.
When environmental interaction is expensive, model-based reinforcement learning offers a solution by planning ahead and avoiding costly mistakes. Model-based agents typically learn a single-step transition model. In this paper, we propose a multi-step model that predicts the outcome of an action sequence with variable length. We show that...More
Full Text (Upload PDF)
PPT (Upload PPT)