Learning Options From Demonstrations: APac-ManCase Study
IEEE Transactions on Games, pp. 91-96, 2018.
Reinforcement learning (RL) is a machine learning paradigm behind many successes in games, robotics, and control applications. RL agents improve through trial-and-error, therefore undergoing a learning phase during which they perform suboptimally. Research effort has been put into optimizing behavior during this period, to reduce its dura...More
Full Text (Upload PDF)
PPT (Upload PPT)