arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05031cs.LG
收藏

用于决策时规划的拉普拉斯表示

Laplacian Representations for Decision-Time Planning

University of Cambridge(剑桥大学)

Dikshant Shehmar, Matthew Schlegel, Matthew E. Taylor, Marlos C. Machado

AI总结:

本文提出利用拉普拉斯表示作为决策时规划的潜在空间,通过多时间尺度捕捉状态空间距离,并基于此设计层次规划算法ALPS,在离线目标条件强化学习任务中优于常用基线。

摘要:

在基于模型的强化学习中,使用学习到的模型进行规划仍然是一个关键挑战。在决策时规划中,状态表示至关重要,因为它们必须支持局部成本计算,同时保持长时程结构。在本文中,我们展示了拉普拉斯表示通过在多时间尺度上捕捉状态空间距离,为规划提供了一个有效的潜在空间。这种表示保留了有意义的距离,并自然地将长时程问题分解为子目标,同时也减轻了长预测范围内出现的复合误差。基于这些特性,我们引入了ALPS,一种层次规划算法,并证明它在来自OGBench(一个以前由无模型方法主导的基准)的离线目标条件强化学习任务选择上优于常用的基线。

英文摘要:

Planning with a learned model remains a key challenge in model-based reinforcement learning (RL). In decision-time planning, state representations are critical as they must support local cost computation while preserving long-horizon structure. In this paper, we show that the Laplacian representation provides an effective latent space for planning by capturing state-space distances at multiple time scales. This representation preserves meaningful distances and naturally decomposes long-horizon problems into subgoals, also mitigating the compounding errors that arise over long prediction horizons. Building on these properties, we introduce ALPS, a hierarchical planning algorithm, and demonstrate that it outperforms commonly used baselines on a selection of offline goal-conditioned RL tasks from OGBench, a benchmark previously dominated by model-free methods.

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。

↑