Planning is an important capability of artificial agents that perform
lo...
This work explores the problem of generating task graphs of real-world
a...
Real-world tasks consist of multiple inter-dependent subtasks (e.g., a d...
We tackle real-world problems with complex structures beyond the pixel-b...
Real world tasks are hierarchical and compositional. Tasks can be compos...
Operating in the real-world often requires agents to learn about a compl...
We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on ...
First-person object-interaction tasks in high-fidelity, 3D, simulated
en...
In batch reinforcement learning (RL), one often constrains a learned pol...
We propose and address a novel few-shot RL problem, where a task is
char...
We introduce a new RL problem where the agent is required to execute a g...