DeepAI AI Chat
Log In Sign Up

Zero-shot Task Adaptation using Natural Language

by   Prasoon Goyal, et al.
The University of Texas at Austin

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.


page 2

page 5

page 12

page 13


Language-guided Task Adaptation for Imitation Learning

We introduce a novel setting, wherein an agent needs to learn a task fro...

Guiding Policies with Language via Meta-Learning

Behavioral skills or policies for autonomous agents are conventionally l...

Reward Learning from Narrated Demonstrations

Humans effortlessly "program" one another by communicating goals and des...

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

Large language models (LMs) have exhibited superior in-context learning ...

One-Shot Learning from a Demonstration with Hierarchical Latent Language

Humans have the capability, aided by the expressive compositionality of ...

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...

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

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