arXiv：cs.LG· Jonghae Park, Sungil Son, Jonghun Shin, Junseo Lee, H. Jin Kim, Benjamin Eysenbach·· 4 小时前
C-Slerp：超球面对比表征解锁规划与探索
Hyperspherical Contrastive Representations Unlock Planning and Exploration
AI 导读
自监督强化学习算法 C-Slerp 无需先验数据、奖励、示范或预训练模型，即可从零学会搭建最多八块积木的塔。该方法用对比表征作为可复用组件，在超球面参数化下通过球面线性插值闭式推断中间路点序列，无需训练高层策略或做图搜索，表征几何还能根据任务难度调整路点数量。实验显示其在长时程导航与机器人操作任务上成功，部分强基线一次都无法成功；消融实验表明固定路点数量会显著降低性能。
正文
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.
| Comments: | Project page: this https URL |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.20409 [cs.LG] |
| (or arXiv:2610.20409v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20409 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jonghae Park [view email]
[v1]
Wed, 14 Oct 2026 16:08:28 UTC (4,603 KB)
来源：arXiv：cs.LG · arxiv.org