EurekAlert!

Multi-constraint reinforcement learning in complex robot environments

FPMCO decomposes multi-constraint RL into KL-projection sub-problems, achieving higher reward with lower computing than second-order rivals on the new SCIG robotics benchmark.
GitHub

Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) ...
IEEE

Deep Reinforcement Learning for Large-Scale Efficient Routing of Electric Vehicles

Abstract: Future smart transportation is anticipated to be much enhanced by autonomous electric vehicles, but efficient routing remains a challenge due to uncertainties and time constraints. Exact ...
IEEE

Deep Reinforcement Learning Based Jamming Strategy Optimization Method Under the INUSRJ Scheme

Abstract: Interrupted non-uniform sampling repeater jamming (INUSRJ) overcomes the inherent periodicity limitations of traditional interrupted sampling repeater jamming (ISRJ). However, optimizing the ...