4 papers
: An Agent-Generates-Agent Framework for Reinforcement Learning Automation
Yuan Wei, Xiaohan Shan, Ran Miao +1
Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This…
PhaseNAS: Language-Model Driven Architecture Search with Dynamic Phase Adaptation
Fei Kong, Xiaohan Shan, Yanwei Hu +1
Neural Architecture Search (NAS) is challenged by the trade-off between search space exploration and efficiency, especially for complex tasks. While recent LLM-based NAS methods ha…
LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning
Yuan Wei, Xiaohan Shan, Jianmin Li
Multi-agent reinforcement learning (MARL) faces two critical bottlenecks distinct from single-agent RL: credit assignment in cooperative tasks and partial observability of environm…
Lifelong Reinforcement Learning with Similarity-Driven Weighting by Large Models
Zhiyi Huang, Xiaohan Shan, Jianmin Li
Lifelong Reinforcement Learning (LRL) holds significant potential for addressing sequential tasks, but it still faces considerable challenges. A key difficulty lies in effectively…