外观
论文arXiv 2610.2040914 天前
超球面对比表征解锁规划与探索
原文链接：Hyperspherical Contrastive Representations Unlock Planning and Exploration（arXiv 2610.20409 · 发布日期：2026-10-14）
Hyperspherical Contrastive Representations Unlock Planning and Exploration
提出自监督强化学习C-Slerp，用超球面对比表征规划中间路标，并在长时程导航和机器人操作中验证。
核心要点
- 目标是在无先验数据、奖励、演示或预训练模型下，从零学习搭建最多八个方块的塔。
- C-Slerp将对比表征作为可复用构件，通过超球面参数化和球面线性插值闭式推断中间路标。
- 表征几何可根据每个目标到达问题的难度，调整所需中间路标数量，无需高层策略或图搜索。
- 实验在长时程导航和机器人操作任务中成功，且在强基线零成功的设置中也有效；固定路标数会显著降级。
验证范围与局限：验证范围为长时程导航和机器人操作任务，包括从零搭建最多八个方块的塔。
英文摘要 (Abstract)
We develop a self-supervised reinforcement learning algorithm that learns to build towers of up to eight cubes from scratch, without prior data, rewards, demonstrations, or pretrained models. Our method, Contrastive Planning via Spherical Linear Interpolation (C-Slerp), uses contrastive representations as reusable building blocks and repeatedly composes them to infer a sequence of intermediate waypoints. Under our hyperspherical parameterization, the learned representations allow intermediate waypoints to be inferred in closed form through spherical linear interpolation, without training a separate high-level policy or performing graph search. Importantly, the representation geometry also tells us how to adjust the number of waypoints based on the difficulty of each goal-reaching problem. Experiments show that our method succeeds on long-horizon navigation and robotic manipulation tasks, including settings where strong baselines fail to achieve a single success. Ablations further show that using a fixed number of waypoints substantially degrades performance, highlighting the importance of adapting the plan to task difficulty.
作者：Jonghae Park, Sungil Son, Jonghun Shin, Junseo Lee, H. Jin Kim, Benjamin Eysenbach
来源
本页事实对应的公开页面，以原文为准。