Self-Initiated Open World Learning for Autonomous AI Agents

by   Bing Liu, et al.
University of Illinois at Chicago

As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can learn by themselves in a self-motivated and self-supervised manner rather than being retrained periodically on the initiation of human engineers using expanded training data. As the real-world is an open environment with unknowns or novelties, detecting novelties or unknowns, gathering ground-truth training data, and incrementally learning the unknowns make the agent more and more knowledgeable and powerful over time. The key challenge is how to automate the process so that it is carried out on the agent's own initiative and through its own interactions with humans and the environment. Since an AI agent usually has a performance task, characterizing each novelty becomes necessary so that the agent can formulate an appropriate response to adapt its behavior to cope with the novelty and to learn from it to improve its future responses and task performance. This paper proposes a theoretic framework for this learning paradigm to promote the research of building self-initiated open world learning agents.


page 1

page 2

page 3

page 4


AI Autonomy: Self-Initiation, Adaptation and Continual Learning

As more and more AI agents are used in practice, it is time to think abo...

Characterizing Novelty in the Military Domain

A critical factor in utilizing agents with Artificial Intelligence (AI) ...

Open-World Learning Without Labels

Open-world learning is a problem where an autonomous agent detects thing...

Evidence of behavior consistent with self-interest and altruism in an artificially intelligent agent

Members of various species engage in altruism–i.e. accepting personal co...

Novelty Accommodating Multi-Agent Planning in High Fidelity Simulated Open World

Autonomous agents acting in real-world environments often need to reason...

OMNI: Open-endedness via Models of human Notions of Interestingness

Open-ended algorithms aim to learn new, interesting behaviors forever. T...

Please sign up or login with your details

Forgot password? Click here to reset