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

Wed Jun 12th 06:30 -- 09:00 PM @ Pacific Ballroom #40

Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While meta-reinforcement learning (meta-RL) algorithms can 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. They also lack mechanisms to reason about task uncertainty when adapting to new tasks, limiting their effectiveness on sparse reward problems. In this paper, we address these challenges by developing an off-policy meta-RL algorithm that disentangles task inference and control. In our approach, we perform online probabilistic filtering of latent task variables to infer how to solve a new task from small amounts of experience. This probabilistic interpretation enables posterior sampling for structured and efficient exploration. We demonstrate how to integrate these task variables with off-policy RL algorithms to achieve both meta-training and adaptation efficiency. Our method outperforms prior algorithms in sample efficiency by 20-100X as well as in asymptotic performance 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