Sample-Efficient Reinforcement Learning Based on Dynamics Models via Meta-policy Optimization
Communications in Computer and Information ScienceCognitive Systems and Information Processing（2022）
关键词
Robot learning, Model-based reinforcement learning, Meta-learning, Model bias
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