[TOC]
- Title: Interactive Grounded Language Understanding in a Collaborative Environment
- Author: Julia Kiseleva et. al.
- Publish Year: 2021
- Review Date: Dec 2021
Summary of paper
The primary goal of the competition is to approach the problem of how to build interactive agents that learn to solve a task while provided with grounded natural language instructions in a collaborative environment.
The split the problem into following concrete research questions, which correspond to separate tasks that can be used to study each component individually before joining all of them into one system
Silent Builder
Environment info
Action space
The agent’s action space might consist of all possible actions in Minecraft. For the current Builder baseline, we offer a discretised version of 18 actions:
- noop, step forward, step backward, step right, step left, turn up, turn down, turn left, turn right, jump, attack, place block, choose block type 1-6.
Sequence of annotation of sub-goals
They annotated each dialog’s sub-goals and stored them in a queue, where each sub-goal corresponds to one specific step instruction from the Architect. At each step, they pop up a sub-task (e.g., in about the middle, build a column five tall) and wait until the agent completes it. If the agent completes this sub-task, they pop up the next sub-task. They trained a matching model to decide if the current sub-task has been finished.