基于掩码潜在变换器的精准高效世界建模
Accurate and Efficient World Modeling with Masked Latent Transformers
AI总结：
EMERALD通过高效掩码潜在变换器实现精准高效的世界建模，首次在1000万环境步骤内超越人类专家性能。
摘要：
Dreamer算法通过训练强大的代理以模拟轨迹在不同环境领域取得了显著性能。然而，其世界模型的潜在空间压缩特性可能导致关键信息丢失，从而影响代理性能。最近的方法如Δ-IRIS和DIAMOND通过训练更准确的世界模型来解决这一限制。然而，这些方法需要直接从像素训练代理，这会降低训练效率，并阻止代理从世界模型学习的内部表示中受益。在本文中，我们提出了一种替代的世界建模方法，该方法既准确又高效。我们引入了EMERALD（高效掩码潜在变换器世界模型），一种使用空间潜在状态和MaskGIT预测来在潜在空间中生成准确轨迹并提高代理性能的世界模型。在Crafter基准测试中，EMERALD实现了新的最先进的性能，成为第一个在1000万环境步骤内超越人类专家性能的方法。我们的方法还成功解锁了所有22个Crafter成就至少一次。
英文摘要：
The Dreamer algorithm has recently obtained remarkable performance across diverse environment domains by training powerful agents with simulated trajectories. However, the compressed nature of its world model's latent space can result in the loss of crucial information, negatively affecting the agent's performance. Recent approaches, such as $Δ$-IRIS and DIAMOND, address this limitation by training more accurate world models. However, these methods require training agents directly from pixels, which reduces training efficiency and prevents the agent from benefiting from the inner representations learned by the world model. In this work, we propose an alternative approach to world modeling that is both accurate and efficient. We introduce EMERALD (Efficient MaskEd latent tRAnsformer worLD model), a world model using a spatial latent state with MaskGIT predictions to generate accurate trajectories in latent space and improve the agent performance. On the Crafter benchmark, EMERALD achieves new state-of-the-art performance, becoming the first method to surpass human experts performance within 10M environment steps. Our method also succeeds to unlock all 22 Crafter achievements at least once during evaluation.
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。
