表示世界模型：在表示中学习状态、转移与可执行计划
Representation World Model: Learning States, Transition and Executable Plans in Representation
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出表示世界模型（RWM），直接在表示空间中学习状态、转移与可执行计划，通过逆动力学监督构建潜在路径实现直接规划，在连续控制和机器人操作任务上验证了有效性。
AI中文摘要：
我们提出了表示世界模型（RWM），该模型直接在表示空间中学习状态、转移和可执行计划。与现有的世界模型通常将潜在表示与显式动力学模型一起学习，并通过搜索、优化或基于策略的预测来执行规划不同，RWM 直接将规划融入所学习的表示几何中。RWM 通过沿着由端点表示构建的潜在路径局部应用逆动力学监督来学习表示几何，要求这些路径保留与任务相关的状态和转移信息。在推理时，规划通过直接构建当前表示与目标表示之间的潜在路径来执行，并利用逆动力学恢复相应的动作，无需递归展开或动作空间搜索。在连续控制基准上的实验证明了 RWM 在直接规划方面的有效性，而机器人操作的结果进一步展示了其扩展到更复杂具身控制任务的潜力。这些结果表明，直接在表示空间中规划为传统世界模型规划提供了一种有前景的替代方案。
英文摘要：
We propose the Representation World Model (RWM), which learns states, transitions, and executable plans directly in representation space. Unlike existing world models that typically learn latent representations together with explicit dynamics models and perform planning through search, optimization, or policy-based prediction, RWM directly incorporates planning into the learned representation geometry. RWM learns the representation geometry by applying inverse-dynamics supervision locally along latent paths constructed from endpoint representations, requiring these paths to preserve task-relevant state and transition information. At inference, planning is performed by directly constructing a latent path between the current and goal representations, with inverse dynamics used to recover the corresponding actions, without recursive rollouts or action-space search. Experiments on continuous-control benchmarks demonstrate the effectiveness of RWM for direct planning, while results on robotic manipulation further show its potential to extend to more complex embodied control tasks. These results suggest that planning directly in representation space provides a promising alternative to conventional world-model planning.
