3 papers
cs.LG2026
Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization
Qijun Liao, Jue Yang, Yiting Kang +3
Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distribution shift, as purely data-driven…
cs.LG2026
Constraint-Enhanced Reinforcement Learning Based on Dynamic Decoupled Spherical Radial Squashing
Qijun Liao, Zhaoxin Yu, Jue Yang
When deploying reinforcement learning policies to physical robots, actuator rate constraints -- hard limits on how fast each joint can move per control step -- are unavoidable. The…
cs.LG2025
Compositional Learning for Modular Multi-Agent Self-Organizing Networks
Qi Liao, Parijat Bhattacharjee
Self-organizing networks face challenges from complex parameter interdependencies and conflicting objectives. This study introduces two compositional learning approaches-Compositio…