Oral
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
Kate Rakelly · Aurick Zhou · Chelsea Finn · Sergey Levine · Deirdre Quillen

Wed Jun 12th 12:15 -- 12:20 PM @ Hall B

Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience, several major challenges preclude their practicality. Current methods rely heavily on on-policy experience, limiting their sample efficiency, and lack mechanisms to reason about task uncertainty when identifying and learning new tasks, limiting their effectiveness in sparse reward problems. In this paper, we aim to address these challenges by developing an off-policy meta-RL algorithm based on online latent task inference. Our method can be interpreted as an implementation of online probabilistic filtering of latent task variables to infer how to solve a new task from small amounts of experience. This probabilistic interpretation also enables posterior sampling for structured exploration. Our method outperforms prior algorithms in asymptotic performance and sample efficiency on several meta-RL benchmarks.

Author Information

Kate Rakelly (UC Berkeley)
Aurick Zhou (UC Berkeley)
Chelsea Finn (Stanford, Google, UC Berkeley)
Chelsea Finn

Chelsea Finn is a research scientist at Google Brain and a post-doctoral scholar at UC Berkeley. In September 2019, she will be joining Stanford's computer science department as an assistant professor. Finn's research interests lie in the ability to enable robots and other agents to develop broadly intelligent behavior through learning and interaction. To this end, Finn has developed deep learning algorithms for concurrently learning visual perception and control in robotic manipulation skills, inverse reinforcement methods for scalable acquisition of nonlinear reward functions, and meta-learning algorithms that can enable fast, few-shot adaptation in both visual perception and deep reinforcement learning. Finn received her Bachelors degree in EECS at MIT, and her PhD in CS at UC Berkeley. Her research has been recognized through an NSF graduate fellowship, a Facebook fellowship, the C.V. Ramamoorthy Distinguished Research Award, and the MIT Technology Review 35 under 35 Award, and her work has been covered by various media outlets, including the New York Times, Wired, and Bloomberg.

Sergey Levine (UC Berkeley)
Sergey Levine

Sergey Levine received a BS and MS in Computer Science from Stanford University in 2009, and a Ph.D. in Computer Science from Stanford University in 2014. He joined the faculty of the Department of Electrical Engineering and Computer Sciences at UC Berkeley in fall 2016. His work focuses on machine learning for decision making and control, with an emphasis on deep learning and reinforcement learning algorithms. Applications of his work include autonomous robots and vehicles, as well as computer vision and graphics. His research includes developing algorithms for end-to-end training of deep neural network policies that combine perception and control, scalable algorithms for inverse reinforcement learning, deep reinforcement learning algorithms, and more.

Deirdre Quillen (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors