- Sungryull Sohn
- Hyunjae Woo
- Jongwook Choi
- lyubing Qiang
- Izzeddin Gur
- Aleksandra Faust
- Honglak Lee
Abstract
We tackle real-world problems with complex structures beyond the pixel-based game or simulator. We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph that defines a set of subtasks and their dependencies that are unknown to the agent. Different from the previous meta-RL methods trying to directly infer the unstructured task embedding, our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks, and use it as a prior to improve the task inference in testing. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks than various existing algorithms such as meta reinforcement learning, hierarchical reinforcement learning, and other heuristic agents.
Research Areas
Learn more about how we do research
We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work