Intrinsically-motivated reinforcement learning for control with continuous actions
2017 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)(2017)
摘要
We propose a more practical method to use empowerment as intrinsic reward within a reinforcement learning setting when states and actions are continuous. Our method builds upon two ideas: i) To take advantage of a new Bellman-like equation of empowerment and ii) to simplify the computation of the local rewards by avoiding the approximation of complex distributions over continuous states and actions.
更多查看译文
关键词
reinforcement learning,deep deterministic policy gradient,continuous actions,intrinsic motivation,empowerment
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