Timezone: »

Reinforcement Learning Beyond Optimization
Benjamin Van Roy

Sat Dec 14 02:00 PM -- 02:40 PM (PST) @

The reinforcement learning problem is often framed as one of quickly optimizing an uncertain Markov decision process. This formulation has led to substantial insight and progress in algorithms and theory. However, this perspective is limiting and can also give rise to poor algorithm designs. I will discuss this issue and how it is addressed by popular reinforcement learning algorithms.

Author Information

Benjamin Van Roy (Stanford University)

More from the Same Authors