ai.hackcv
论文精选 65arXiv

Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control· 注意执行差距:控制模型中的动作语义不匹配

World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay, packet loss, reordering, and actuator buffering. We study how asynchronous execution changes the action semantics assumed within world-model controllers, rather than treating it only as an external control disturbance. Through controlled interventions, we identify two architecture-dependent failure modes: planning-based controllers such as TD-MPC2 suffer from a future-action timeline mismatch between imagined and executed action sequences, while recurrent world models such as DreamerV3 can attribute observed transitions to commands that were not actually applied. Our analysis shows that TD-MPC2 requires the corre

AI 解读论文

研究世界模型控制器中的动作语义不匹配问题

核心方法
通过控制干预识别了两种架构依赖的失败模式,分析了TD-MPC2和DreamerV3在异步执行环境下的表现差异
适合谁读
研究者
要解决的问题
解决由于执行异步性导致的动作语义与世界模型控制器假设之间的不一致
关键实验
通过模拟异步执行环境下的控制任务,对比分析了不同控制器的性能
主要贡献
揭示了异步执行对动作语义的影响,为设计更鲁棒的世界模型控制器提供了理论基础
意义与局限
提高了对世界模型中执行异步性问题的认识,有助于开发更适应实际环境的AI系统,但仍需进一步研究具体的解决方案
领域:cs.AI作者:Shengtao Wen、Xiang Chen、Yu Tian
相关推荐
论文精选 65已解读

Simulated Control Evals· 模拟控制评估

Control evaluations measure whether safeguards can prevent an AI model from causing undesi…

领域:cs.AI作者:Jeffrey Olmo、David Zhang、Tyler Tracy
📎 arXiv🕒 10-23 01:26🔗 arxiv.org

本站内容由 LLM 精选聚合,原文版权归 arXiv 所有 · 摘录仅供参考