An empirical evaluation of active inference in multi-armed bandits

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.

References in corpus (10)

• Bayesian Online Changepoint Detection
• Active inference on discrete state-spaces: a synthesis
• Bayesian Reinforcement Learning: A Survey
• Deep Active Inference
• Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit
• Taming Non-stationary Bandits: A Bayesian Approach
• Thompson Sampling in Switching Environments with Bayesian Online Change Point Detection
• Hedging the Drift: Learning to Optimize under Non-Stationarity
• Deep active inference agents using Monte-Carlo methods
• Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits

Cited by in corpus (8)

• A taxonomy of surprise definitions
• On efficient computation in active inference
• Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
• Chance-Constrained Active Inference
• Observation-Augmented Contextual Multi-Armed Bandits for Robotic Search and Exploration
• Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker
• Maximum entropy exploration in contextual bandits with neural networks and energy based models
• Active Inference in Contextual Multi-Armed Bandits for Autonomous Robotic Exploration