Training AI agents for complex problems, such as controllable content generation, requires integrating all sources of experiences (data, cost, constraints, info of related tasks) in learning. Past decades of research has led to a multitude of learning algorithms for ingesting different experiences. However, creating solutions based on such a bewildering marketplace of algorithms demands strong ML expertise and bespoke innovations. This talk will present an alternative approach to creating solutions from a unifying perspective. I will show that many of the popular algorithms in supervised learning, constraint-driven learning, reinforcement learning, etc, indeed share a common succinct formulation and can be reduced to a single algorithm that uses different experiences in the same way. This allows us to create solutions by simply plugging arbitrary experiences in learning, and to enable new learning capabilities by repurposing off-the-shelf algorithms.
Zhiting Hu is a PhD student in the Machine Learning Department at CMU. He received his B.S. from Peking University. His research interests lie in the broad area of machine learning. His research was recognized with best demo nomination at ACL2019, best paper award at ICLR 2019 DRL workshop, outstanding paper award at ACL2016, and IBM Fellowship.
Faculty Host: Bo Li