
TL;DR
This paper introduces a computational model of flow for AI agents, using meta-control to optimize performance by matching agent abilities with environmental complexity, inspired by human flow psychology.
Contribution
It presents a novel meta-control framework based on flow theory, applicable across various AI control policies, and demonstrates its effectiveness in a synthetic test environment.
Findings
Promising results in a synthetic testbed
Meta-control improves AI performance by aligning abilities and task complexity
Open avenues for future research in AI flow modeling
Abstract
The psychological state of flow has been linked to optimizing human performance. A key condition of flow emergence is a match between the human abilities and complexity of the task. We propose a simple computational model of flow for Artificial Intelligence (AI) agents. The model factors the standard agent-environment state into a self-reflective set of the agent's abilities and a socially learned set of the environmental complexity. Maximizing the flow serves as a meta control for the agent. We show how to apply the meta-control policy to a broad class of AI control policies and illustrate our approach with a specific implementation. Results in a synthetic testbed are promising and open interesting directions for future work.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFlow Experience in Various Fields · Reinforcement Learning in Robotics · Evacuation and Crowd Dynamics
