Learning From Stories: Using Crowdsourced Narratives to Train Virtual Agents
By Brent Harrison, Mark O. Riedl. 2021
11 citations recorded by the source corpus.
In this work we introduce Quixote, a system that makes programming virtual agents more accessible to non-programmers by enabling these agents to be trained using the sociocultural knowledge present in stories. Quixote uses a corpus of exemplar stories to automatically engineer a reward function that is used to train virtual agents to exhibit desired behaviors using reinforcement learning. We show the effectiveness of our system with a case study conducted in a virtual environment called Robbery World that simulates a bank robbery scenario. In this case study, we use a corpus of stories crowdsourced from Amazon Mechanical Turk to guide learning. We evaluate Quixote under a variety of different conditions to determine the overall effectiveness of the system in Robbery World.
Subfields: Artificial Intelligence, LLM Agents & Tool Use
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Igor Mordatch
- Pieter Abbeel
- Deepak Pathak
- Chelsea Finn
- Trevor Darrell
- Wenlong Huang
- Abhinav Kumar Gupta
In LLM Agents & Tool Use
- Igor Mordatch
- Pieter Abbeel
- Stefano V. Albrecht
- Filippos Christianos
- Georgios Papoudakis
- Zongqing Lu
- Akifumi Wachi
- Yi Wu
Citations in the corpus
- Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents (2022, background): “unstructured text: the tasks evaluated are often generated from a handful of templates, which do not resemble the highly diverse activities that humans perform in daily lives [14, 20].”