The Value of Reward Lookahead in Reinforcement Learning

arXiv:2403.11637v1 Announce Type: new
Abstract: In reinforcement learning (RL), agents sequentially interact with changing environments while aiming to maximize the obtained rewards. Usually, rewards are observed only after acting, and so the goal is to maximize the expected cumulative reward. Yet, in many practical settings, reward information is observed in advance -- prices are observed before performing transactions; nearby traffic information is partially known; and goals are oftentimes given to agents prior to the interaction. In this work, we aim …

abstract acting advance agents arxiv cs.lg environments information practical reinforcement reinforcement learning stat.ml type value