arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.19634cs.LGcs.AIstat.ML
收藏

基于跳跃世界模型的组合规划

Compositional Planning with Jumpy World Models

FAIR at Meta;Mila -- Qu\'ebec AI Institute;McGill University

Jesse Farebrother, Matteo Pirotta, Andrea Tirinzoni, Marc G. Bellemare, Alessandro Lazaric, Ahmed Touati

AI总结:

本文提出基于跳跃世界模型的组合规划方法,通过学习多步动态预测模型提升长时间任务的规划性能,实现复杂任务的解决。

摘要:

具备时间抽象的规划能力对于智能决策至关重要。与其在原始动作上进行推理,我们研究能够将预训练的策略组合成时间扩展动作的智能体,从而解决单个策略无法完成的复杂任务。这种组合规划仍然难以实现,因为长时间预测中累积的误差使估计由策略序列诱导的访问分布变得困难。受arXiv:2206.08736中引入的几何策略组合框架的启发,我们通过学习多步动态的预测模型——所谓的跳跃世界模型,以非策略方式捕捉由预训练策略在多个时间尺度上引起的状态占用。基于时间差分流(arXiv:2503.09817),我们通过一种新的一致性目标来增强这些模型,使不同时间尺度上的预测保持一致,从而提高长时间预测的准确性。我们进一步展示了如何将这些生成预测结合起来,以估计执行任意策略序列在不同时间尺度上的价值。实验表明,使用跳跃世界模型的组合规划在广泛的基策略上显著提高了零样本性能,在具有挑战性的操作和导航任务中,相对于使用原始动作进行规划,在长时间任务上平均提高了200%的相对性能。

英文摘要:

The ability to plan with temporal abstractions is central to intelligent decision-making. Rather than reasoning over primitive actions, we study agents that compose pre-trained policies as temporally extended actions, enabling solutions to complex tasks that no constituent alone can solve. Such compositional planning remains elusive as compounding errors in long-horizon predictions make it challenging to estimate the visitation distribution induced by sequencing policies. Motivated by the geometric policy composition framework introduced in arXiv:2206.08736, we address these challenges by learning predictive models of multi-step dynamics -- so-called jumpy world models -- that capture state occupancies induced by pre-trained policies across multiple timescales in an off-policy manner. Building on Temporal Difference Flows (arXiv:2503.09817), we enhance these models with a novel consistency objective that aligns predictions across timescales, improving long-horizon predictive accuracy. We further demonstrate how to combine these generative predictions to estimate the value of executing arbitrary sequences of policies over varying timescales. Empirically, we find that compositional planning with jumpy world models significantly improves zero-shot performance across a wide range of base policies on challenging manipulation and navigation tasks, yielding, on average, a 200% relative improvement over planning with primitive actions on long-horizon tasks.

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。

↑