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.
Kate Rakelly (UC Berkeley)
More from the Same Authors
2021 Poster: Which Mutual-Information Representation Learning Objectives are Sufficient for Control? »
Kate Rakelly · Abhishek Gupta · Carlos Florensa · Sergey Levine
2020 : Q/A for invited talk #6 »
2019 Workshop: Robot Learning: Control and Interaction in the Real World »
Roberto Calandra · Markus Wulfmeier · Kate Rakelly · Sanket Kamthe · Danica Kragic · Stefan Schaal · Markus Wulfmeier