Dreamer-CDP: 通过连续确定性表示预测改进无重建世界模型
Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction
AI总结：
本文提出Dreamer-CDP，通过连续确定性表示预测提升世界模型性能，在Crafter环境中达到与传统重建方法相当的性能。
摘要：
基于强化学习（MBRL）的智能体在高维观测空间中（如Dreamer）依赖于学习抽象表示以实现有效规划和控制。现有方法通常在观测空间中使用基于重建的目标，这可能导致表示对任务无关的细节敏感。最近的替代方法用辅助动作预测头或视图增强策略替代重建，但在Crafter环境中表现不如基于重建的方法。我们通过引入一种基于连续确定性表示的JEPA式预测器，缩小了Dreamer与无重建模型之间的差距。我们的方法在Crafter环境中达到与Dreamer相当的性能，证明了在该基准上无需重建目标的有效世界模型学习。
英文摘要：
Model-based reinforcement learning (MBRL) agents operating in high-dimensional observation spaces, such as Dreamer, rely on learning abstract representations for effective planning and control. Existing approaches typically employ reconstruction-based objectives in the observation space, which can render representations sensitive to task-irrelevant details. Recent alternatives trade reconstruction for auxiliary action prediction heads or view augmentation strategies, but perform worse in the Crafter environment than reconstruction-based methods. We close this gap between Dreamer and reconstruction-free models by introducing a JEPA-style predictor defined on continuous, deterministic representations. Our method matches Dreamer's performance on Crafter, demonstrating effective world model learning on this benchmark without reconstruction objectives.
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。
