Ruocheng Wang

Ruocheng Wang

Auto-generated profile, based on publicly available information

Ruocheng Wang

Stanford University, Stanford, United States of America

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 December 2024
Verified
Conference Paper
Open access
RWRuocheng Wang
Ruocheng Wang
PXPei Xu
Pei Xu
HSHaochen Shi
Haochen Shi
ESElizabeth Schumann
Elizabeth Schumann
CLC. Karen Liu
C. Karen Liu


4 December 2025 in ACM Transactions on Graphics
Verified
Journal Article
Open access
PXPei Xu
Pei Xu
ZWZhen Wu
Zhen Wu
RWRuocheng Wang
Ruocheng Wang
VSVishnu Sarukkai
Vishnu Sarukkai
KFKayvon Fatahalian
Kayvon Fatahalian
CLC. Karen Liu
C. Karen Liu
Learning a control policy for a multi-phase, long-horizon task, such as basketball maneuvers, remains challenging for reinforcement learning approaches due to the need for seamless policy composition and transitions between skills. A long-horizon task typically consists of distinct subtasks with well-defined goals, separated by transitional subtasks with unclear goals but critical to the success of the entire task. Existing methods like the mixture of experts and skill chaining struggle with tasks where individual policies do not share significant commonly explored states or lack well-defined initial and terminal states between different phases. In this paper, we introduce a novel policy integration framework to enable the composition of drastically different motor skills in multi-phase long-horizon tasks with ill-defined intermediate states. Based on that, we further introduce a high-level soft router to enable seamless and robust transitions between the subtasks. We evaluate our framework on a set of fundamental basketball skills and challenging transitions. Policies trained by our approach can effectively control the simulated character to interact with the ball and accomplish the long-horizon task specified by real-time user commands, without relying on ball trajectory references.