让机器人自动发现新动作，大幅缩短任务规划时间。
SLAP: Shortcut Learning for Abstract Planning
- 用无模型强化学习在已有抽象动作图中学习捷径路径。
- 计划长度减少超50%，任务成功率显著高于传统方法。
- 适合需要灵活策略的复杂机器人任务场景。
长时程决策问题在稀疏奖励、连续状态与动作环境下仍是人工智能与机器人领域的核心挑战。任务与运动规划（TAMP）通过分层抽象动作（选项）来应对该挑战，但这些选项需人工定义，限制了智能体仅能执行人类已知的行为（如抓取、放置、移动）。本文提出快捷学习抽象规划（SLAP），利用现有TAMP选项自动发现新的抽象动作。核心思想是使用无模型强化学习，在原有选项生成的抽象规划图中学习捷径。无需额外假设或输入，该方法所得方案比纯规划更短，且任务成功率高于平面与分层强化学习。定性上，SLAP发现了动态物理即兴动作（如拍击、晃动、擦拭），与人工定义动作显著不同。在四个仿真机器人环境中验证表明，SLAP可解决并泛化至多种任务，整体计划长度减少超过50%，持续优于规划与强化学习基线。
原文摘要 · Abstract (English)
Long-horizon decision-making with sparse rewards and continuous states and actions remains a fundamental challenge in AI and robotics. Task and motion planning (TAMP) is a model-based framework that addresses this challenge by planning hierarchically with abstract actions (options). These options are manually defined, limiting the agent to behaviors that we as human engineers know how to program (pick, place, move). In this work, we propose Shortcut Learning for Abstract Planning (SLAP), a method that leverages existing TAMP options to automatically discover new ones. Our key idea is to use model-free reinforcement learning (RL) to learn shortcuts in the abstract planning graph induced by the existing options in TAMP. Without any additional assumptions or inputs, shortcut learning leads to shorter solutions than pure planning, and higher task success rates than flat and hierarchical RL. Qualitatively, SLAP discovers dynamic physical improvisations (e.g., slap, wiggle, wipe) that differ significantly from the manually-defined ones. In experiments in four simulated robotic environments, we show that SLAP solves and generalizes to a wide range of tasks, reducing overall plan lengths by over 50% and consistently outperforming planning and RL baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。