When Should a World Model Move? Loss-Conditioned State Execution· 世界模型何时应移动？
We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain the current state. Predictive informativeness alone, however, does not establish whether an update will reduce downstream loss. Occurrence ranking can approach perfection while persistence remains the unique absolute-loss Bayes action. Two transition laws can also share occurrence information and conditional variance yet require opposite absolute-loss decisions. We formalize state movability as the existence of a loss-reducing feasible correction and distinguish it from the benefit of a particular proposal. Our method constructs a loss-specific feasible proposal from a predictive distribution and evaluates its groupwise bounded-loss gain o
提出损失条件状态执行方法，解决世界模型何时更新问题。
- 核心方法
- 通过构建损失特定的可行提案，并评估其有界损失增益，来决定是否执行世界模型的状态更新。
- 适合谁读
- 研究者
- 要解决的问题
- 现有世界模型的更新机制仅依赖于预测信息量，无法确保更新能够减少下游损失。
- 关键实验
- 未提供
- 主要贡献
- 形式化定义了状态可移动性，并提出了一个模型无关的方法来决策模型状态更新。
- 意义与局限
- 该方法能够提高世界模型在实际应用中的效用和稳定性，但需要进一步的实验证明。