The use of Potential Based Reward Shaping (PBRS) has shown great promise in the ongoing research effort to tackle sample inefficiency in Reinforcement Learning (RL). However, the choice of the potential function is critical for this technique to be effective. Additionally, RL techniques are usually constrained to use a finite horizon for computational limitations. This introduces a bias when using PBRS, thus adding an additional layer of complexity. In this paper, we leverage abstractions to automatically produce a "good" potential function. We analyse the bias induced by finite horizons in the context of PBRS producing novel insights. Finally, to asses sample efficiency and performance impact, we evaluate our approach on four environments including a goal-oriented navigation task and three Arcade Learning Environments (ALE) games demonstrating that we can reach the same level of performance as CNN-based solutions with a simple fully-connected network.

翻译：基于势能的奖励塑形（PBRS）在解决强化学习（RL）样本效率低下的持续研究中展现出巨大潜力。然而，势函数的选择对该技术的有效性至关重要。此外，由于计算限制，强化学习技术通常被约束在有限时间范围内使用。这会在使用PBRS时引入偏差，从而增加额外的复杂性。本文利用抽象方法自动生成“优质”势函数，分析了有限时间范围在PBRS情境下产生的偏差，并提出了新颖见解。最后，为评估样本效率与性能影响，我们在四个环境（包括一个面向目标的导航任务和三个Arcade学习环境游戏）中测试了所提方法，结果表明：使用简单的全连接网络即可达到与基于CNN的解决方案相同的性能水平。