An Offline-to-online Reinforcement Learning Approach Based on Multi-Action Evaluation with Policy Extension
Applied Intelligence（2024）
关键词
Offline-to-online reinforcement learning,Policy extension,Action-oriented,Multi-action evaluation
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要