TWOSOME: an Efficient Online Framework to Align LLMs with Embodied Environments Via Reinforcement LearningWeihao Tan,Wentao Zhang,Shanqi Liu,Longtao Zheng,Xinrun Wang,Bo AnInt J Artif Intell Robotics Res(2024)引用 0|浏览13AI 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