Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
作者： Matteo Leonetti , Bei Peng , Peter Stone , Matthew E. Taylor , Sanmit Narvekar
DOI:
关键词:
摘要: Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. Despite many advances over …
harvard.edu
arxiv-vanity.com
acm.org参考文章(0)