`

Timezone: »

 
Poster
Discovering and Achieving Goals via World Models
Russell Mendonca · Oleh Rybkin · Kostas Daniilidis · Danijar Hafner · Deepak Pathak

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @ None #None

How can artificial agents learn to solve many diverse tasks in complex visual environments without any supervision? We decompose this question into two challenges: discovering new goals and learning to reliably achieve them. Our proposed agent, Latent Explorer Achiever (LEXA), addresses both challenges by learning a world model from image inputs and using it to train an explorer and an achiever policy via imagined rollouts. Unlike prior methods that explore by reaching previously visited states, the explorer plans to discover unseen surprising states through foresight, which are then used as diverse targets for the achiever to practice. After the unsupervised phase, LEXA solves tasks specified as goal images zero-shot without any additional learning. LEXA substantially outperforms previous approaches to unsupervised goal reaching, both on prior benchmarks and on a new challenging benchmark with 40 test tasks spanning across four robotic manipulation and locomotion domains. LEXA further achieves goals that require interacting with multiple objects in sequence. Project page: https://orybkin.github.io/lexa/

Author Information

Russell Mendonca (Carnegie Mellon University)
Oleh Rybkin (University of Pennsylvania)

I am a Ph.D. student in the GRASP laboratory at the University of Pennsylvania, where I work on computer vision and deep learning with Kostas Daniilidis. Previously, I received my bachelor's degree from Czech Technical University in Prague, where I was advised by Tomas Pajdla. I have spent two summers at INRIA and TiTech, with Josef Sivic and Akihiko Torii respectively. I am working in artificial intelligence, computer vision, and robotics. More specifically, my main interest is machine understanding of intuitive physics for real-world robotic manipulation. My latest work has been on motion understanding via video prediction. During my bachelor's, I also worked on camera geometry for structure from motion.

Kostas Daniilidis (University of Pennsylvania)
Danijar Hafner (Google)
Deepak Pathak (Carnegie Mellon University)

More from the Same Authors