An empirical evaluation of active inference in multi-armed bandits

TL;DR

This paper empirically evaluates an active inference algorithm for multi-armed bandit problems, comparing its performance to traditional algorithms in stationary and switching environments, highlighting its strengths in dynamic settings.

Contribution

It introduces an efficient approximate active inference algorithm and demonstrates its superior performance in non-stationary bandit problems compared to existing methods.

Findings

Active inference performs poorly in stationary bandits.

It significantly outperforms in switching bandit scenarios.

Results support active inference as a promising approach for dynamic decision problems.

Abstract

A key feature of sequential decision making under uncertainty is a need to balance between exploiting--choosing the best action according to the current knowledge, and exploring--obtaining information about values of other actions. The multi-armed bandit problem, a classical task that captures this trade-off, served as a vehicle in machine learning for developing bandit algorithms that proved to be useful in numerous industrial applications. The active inference framework, an approach to sequential decision making recently developed in neuroscience for understanding human and animal behaviour, is distinguished by its sophisticated strategy for resolving the exploration-exploitation trade-off. This makes active inference an exciting alternative to already established bandit algorithms. Here we derive an efficient and scalable approximate active inference algorithm and compare it to two state-of-the-art bandit algorithms: Bayesian upper confidence bound and optimistic Thompson sampling. This comparison is done on two types of bandit problems: a stationary and a dynamic switching bandit. Our empirical evaluation shows that the active inference algorithm does not produce efficient long-term behaviour in stationary bandits. However, in the more challenging switching bandit problem active inference performs substantially better than the two state-of-the-art bandit algorithms. The results open exciting venues for further research in theoretical and applied machine learning, as well as lend additional credibility to active inference as a general framework for studying human and animal behaviour.