8个标记的规划：一种用于潜在世界模型的紧凑离散标记器
Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
AI总结：
本文提出CompACT，一种将观测压缩为8个标记的离散标记器，显著降低计算成本并提升规划效率，为潜在世界模型的实际应用提供可行方案。
摘要：
世界模型提供了一个强大的框架，用于根据动作或指令模拟环境动态，从而实现下游任务，如动作规划或策略学习。最近的方法利用世界模型作为学习模拟器，但将其应用于决策时间的规划在实时控制中计算上是不可行的。关键的瓶颈在于潜在表示：传统标记器将每个观测编码成数百个标记，使规划变得缓慢且资源消耗大。为了解决这一问题，我们提出了CompACT，一种离散标记器，将每个观测压缩成最多8个标记，大幅降低计算成本，同时保留规划所需的必要信息。一个使用CompACT标记器的行动条件世界模型实现了与数量级更快的规划相竞争的规划性能，为世界模型在现实世界中的部署提供了实际的一步。
英文摘要：
World models provide a powerful framework for simulating environment dynamics conditioned on actions or instructions, enabling downstream tasks such as action planning or policy learning. Recent approaches leverage world models as learned simulators, but its application to decision-time planning remains computationally prohibitive for real-time control. A key bottleneck lies in latent representations: conventional tokenizers encode each observation into hundreds of tokens, making planning both slow and resource-intensive. To address this, we propose CompACT, a discrete tokenizer that compresses each observation into as few as 8 tokens, drastically reducing computational cost while preserving essential information for planning. An action-conditioned world model that occupies CompACT tokenizer achieves competitive planning performance with orders-of-magnitude faster planning, offering a practical step toward real-world deployment of world models.
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。
