Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model.
Annual Conference on Neural Information Processing Systems（2021）
摘要
Use the "Report an Issue" link to request a name change.
更多查看译文
关键词
leave-one-out analysis,linear transition model,model-based reinforcement learning,sample complexity,vanilla Q-learning
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