DeepAI AI Chat
Log In Sign Up

Zero-shot Task Adaptation using Natural Language

06/05/2021
by   Prasoon Goyal, et al.
The University of Texas at Austin
0

Imitation learning and instruction-following are two common approaches to communicate a user's intent to a learning agent. However, as the complexity of tasks grows, it could be beneficial to use both demonstrations and language to communicate with an agent. In this work, we propose a novel setting where an agent is given both a demonstration and a description, and must combine information from both the modalities. Specifically, given a demonstration for a task (the source task), and a natural language description of the differences between the demonstrated task and a related but different task (the target task), our goal is to train an agent to complete the target task in a zero-shot setting, that is, without any demonstrations for the target task. To this end, we introduce Language-Aided Reward and Value Adaptation (LARVA) which, given a source demonstration and a linguistic description of how the target task differs, learns to output a reward / value function that accurately describes the target task. Our experiments show that on a diverse set of adaptations, our approach is able to complete more than 95 template-based descriptions, and more than 70 language.

READ FULL TEXT

page 2

page 5

page 12

page 13

01/24/2023

Language-guided Task Adaptation for Imitation Learning

We introduce a novel setting, wherein an agent needs to learn a task fro...
11/19/2018

Guiding Policies with Language via Meta-Learning

Behavioral skills or policies for autonomous agents are conventionally l...
04/27/2018

Reward Learning from Narrated Demonstrations

Humans effortlessly "program" one another by communicating goals and des...
05/24/2023

Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations

Large language models (LMs) have exhibited superior in-context learning ...
03/09/2022

One-Shot Learning from a Demonstration with Hierarchical Latent Language

Humans have the capability, aided by the expressive compositionality of ...
12/07/2021

Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft

Real-world tasks of interest are generally poorly defined by human-reada...
08/01/2023

Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models

Today, large language models (LLMs) are taught to use new tools by provi...