Timezone: »

An inference perspective on meta-reinforcement learning
Kate Rakelly

Fri Dec 11 10:01 AM -- 10:26 AM (PST) @ None

While meta-learning algorithms are often viewed as algorithms that learn to learn, an alternative viewpoint frames meta-learning as inferring a hidden task variable from experience consisting of observations and rewards. From this perspective, learning-to-learn is learning-to-infer. This viewpoint can be useful in solving problems in meta-reinforcement learning, which I’ll demonstrate through two examples: (1) enabling off-policy meta-learning and (2) performing efficient meta-reinforcement learning from image observations. Finally, I’ll discuss how I think this perspective can inform future meta-reinforcement learning research.

Author Information

Kate Rakelly (UC Berkeley)

More from the Same Authors