Timezone: »

Environment Generation for Zero-Shot Compositional Reinforcement Learning
Izzeddin Gur · Natasha Jaques · Yingjie Miao · Jongwook Choi · Manoj Tiwari · Honglak Lee · Aleksandra Faust

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @ None #None

Many real-world problems are compositional – solving them requires completing interdependent sub-tasks, either in series or in parallel, that can be represented as a dependency graph. Deep reinforcement learning (RL) agents often struggle to learn such complex tasks due to the long time horizons and sparse rewards. To address this problem, we present Compositional Design of Environments (CoDE), which trains a Generator agent to automatically build a series of compositional tasks tailored to the RL agent’s current skill level. This automatic curriculum not only enables the agent to learn more complex tasks than it could have otherwise, but also selects tasks where the agent’s performance is weak, enhancing its robustness and ability to generalize zero-shot to unseen tasks at test-time. We analyze why current environment generation techniques are insufficient for the problem of generating compositional tasks, and propose a new algorithm that addresses these issues. Our results assess learning and generalization across multiple compositional tasks, including the real-world problem of learning to navigate and interact with web pages. We learn to generate environments composed of multiple pages or rooms, and train RL agents capable of completing wide-range of complex tasks in those environments. We contribute two new benchmark frameworks for generating compositional tasks, compositional MiniGrid and gMiniWoB for web navigation. CoDE yields 4x higher success rate than the strongest baseline, and demonstrates strong performance of real websites learned on 3500 primitive tasks.

Author Information

Izzeddin Gur (Google)
Natasha Jaques (Google Brain, UC Berkeley)
Yingjie Miao (Google)
Jongwook Choi (University of Michigan)
Manoj Tiwari
Honglak Lee (U. Michigan)
Aleksandra Faust (Google Brain)

Aleksandra Faust is a Senior Research Engineer at Google Brain, specializing in robot intelligence. Previously, Aleksandra led machine learning efforts for self-driving car planning and controls in Waymo and Google X, and was a researcher in Sandia National Laboratories, where she worked on satellites and other remote sensing applications. She earned a Ph.D. in Computer Science at the University of New Mexico (with distinction), a Master’s in Computer Science from University of Illinois at Urbana-Champaign, and a Bachelor’s in Mathematics from University of Belgrade, Serbia. Her research interests include reinforcement learning, adaptive motion planning, and machine learning for decision-making. Aleksandra won Tom L. Popejoy Award for the best doctoral dissertation at the University of New Mexico in Engineering, Mathematics, and Sciences in the period of 2011-2014. She was also awarded with the Best Paper in Service Robotics at ICRA 2018, Sandia National Laboratories’ Doctoral Studies Program and New Mexico Space Grant fellowships, as well as the Outstanding Graduate Student in Computer Science award. Her work has been featured in the New York Times.​

More from the Same Authors