5 papers
Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion
Tianyang Wu, Hanwei Guo, Yuhang Wang +6
Reinforcement learning has shown strong promise for quadrupedal agile locomotion, even with proprioception-only sensing. In practice, however, sim-to-real gap and reward overfittin…
Hybrid Distillation with CoT Guidance for Edge-Drone Control Code Generation
Yizhan Feng, Hichem Snoussi, Yuhang Wang +3
With large language models demonstrating significant potential in code generation tasks, their application to onboard control of resource-constrained Unmanned Aerial Vehicles has e…
Learning from Risk: LLM-Guided Generation of Safety-Critical Scenarios with Prior Knowledge
Yuhang Wang, Heye Huang, Zhenhua Xu +3
Autonomous driving faces critical challenges in rare long-tail events and complex multi-agent interactions, which are scarce in real-world data yet essential for robust safety vali…
Playing Non-Embedded Card-Based Games with Reinforcement Learning
Tianyang Wu, Lipeng Wan, Yuhang Wang +2
Significant progress has been made in AI for games, including board games, MOBA, and RTS games. However, complex agents are typically developed in an embedded manner, directly acce…
Bootstrapped Model Predictive Control
Yuhang Wang, Hanwei Guo, Sizhe Wang +2
Model Predictive Control (MPC) has been demonstrated to be effective in continuous control tasks. When a world model and a value function are available, planning a sequence of acti…