Juntao Liu

A Projection-based Exploration Method for Multi-Agent Coordination

2024

In multi-agent reinforcement learning (MARL), states with high exploration value are difficult to be identified and coordinately visited, resulting in low learning efficiency. To this end, a projection-based exploration method for multi-agent coordination (PEMAC) is …

Coevolutionary Neural Dynamics Considering Multiple Strategies for Nonconvex Optimization

2025 · Tsinghua Science & Technology

In the field of practical applications, the solution of nonconvex optimization problems plays a crucial role. However, many practical applications often encounter perturbations that may affect solutions to relevant nonconvex problems. Such perturbations are typically …