Active Inference in Contextual Multi-Armed Bandits for Autonomous Robotic Exploration

TL;DR

This paper demonstrates that active inference effectively balances exploration and exploitation in contextual multi-armed bandit problems for autonomous robotic exploration, especially in realistic noisy environments, outperforming standard methods.

Contribution

It applies neuro-inspired active inference to real-world scenarios, specifically mineralogical survey site selection, showing improved efficiency and adaptability over traditional bandit strategies.

Findings

Active inference requires fewer iterations than standard bandit approaches.

It adapts effectively to changing expert preferences.

Performance is robust in noisy, biased real-world data.

Abstract

Autonomous selection of optimal options for data collection from multiple alternatives is challenging in uncertain environments. When secondary information about options is accessible, such problems can be framed as contextual multi-armed bandits (CMABs). Neuro-inspired active inference has gained interest for its ability to balance exploration and exploitation using the expected free energy objective function. Unlike previous studies that showed the effectiveness of active inference based strategy for CMABs using synthetic data, this study aims to apply active inference to realistic scenarios, using a simulated mineralogical survey site selection problem. Hyperspectral data from AVIRIS-NG at Cuprite, Nevada, serves as contextual information for predicting outcome probabilities, while geologists' mineral labels represent outcomes. Monte Carlo simulations assess the robustness of active inference against changing expert preferences. Results show that active inference requires fewer iterations than standard bandit approaches with real-world noisy and biased data, and performs better when outcome preferences vary online by adapting the selection strategy to align with expert shifts.