利用离散表示进行持续强化学习
Harnessing Discrete Representations For Continual Reinforcement Learning
AI总结：
本研究针对强化学习中离散观测表示的作用开展实证研究，验证其在世界模型学习、无模型RL及持续RL中相比连续表示的优势，揭示性能提升的潜在原因，为持续RL智能体更快适配提供支撑。
摘要：
强化学习（RL）智能体仅依靠环境观测做出决策，因此高度依赖这些观测的表示。尽管近期一些突破采用了基于向量的观测分类表示（通常称为离散表示），但鲜有研究明确评估这一选择的重要性。在本研究中，我们针对强化学习场景下将观测表示为分类值向量的优势开展了全面的实证研究。我们在世界模型学习、无模型强化学习以及最终的持续强化学习问题上进行评估，这些场景下离散表示的优势与问题设定的需求最为契合。研究发现，与传统的连续表示相比，基于离散表示学习的世界模型能以更低的容量更准确地建模更多环境信息，且采用离散表示训练的智能体能用更少数据学习到更优策略。在持续强化学习场景中，这些优势转化为智能体更快的适应速度。此外，我们的分析表明，观测到的性能提升可归因于潜在向量中包含的信息，以及离散表示本身的编码方式。
英文摘要：
Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations. Though some recent breakthroughs have used vector-based categorical representations of observations, often referred to as discrete representations, there is little work explicitly assessing the significance of such a choice. In this work, we provide a thorough empirical investigation of the advantages of representing observations as vectors of categorical values within the context of reinforcement learning. We perform evaluations on world-model learning, model-free RL, and ultimately continual RL problems, where the benefits best align with the needs of the problem setting. We find that, when compared to traditional continuous representations, world models learned over discrete representations accurately model more of the world with less capacity, and that agents trained with discrete representations learn better policies with less data. In the context of continual RL, these benefits translate into faster adapting agents. Additionally, our analysis suggests that the observed performance improvements can be attributed to the information contained within the latent vectors and potentially the encoding of the discrete representation itself.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
