Active Inference for Autonomous Decision-Making with Contextual Multi-Armed Bandits
This work addresses decision-making in robotics by proposing a novel method for contextual multi-armed bandits, offering incremental improvements in efficiency and performance.
The study tackled autonomous decision-making under uncertainty by applying active inference to contextual multi-armed bandits, introducing approximation methods for expected free energy, and demonstrated that it requires far fewer iterations to identify optimal options and achieves superior cumulative regret compared to other strategies.
In autonomous robotic decision-making under uncertainty, the tradeoff between exploitation and exploration of available options must be considered. If secondary information associated with options can be utilized, such decision-making problems can often be formulated as contextual multi-armed bandits (CMABs). In this study, we apply active inference, which has been actively studied in the field of neuroscience in recent years, as an alternative action selection strategy for CMABs. Unlike conventional action selection strategies, it is possible to rigorously evaluate the uncertainty of each option when calculating the expected free energy (EFE) associated with the decision agent's probabilistic model, as derived from the free-energy principle. We specifically address the case where a categorical observation likelihood function is used, such that EFE values are analytically intractable. We introduce new approximation methods for computing the EFE based on variational and Laplace approximations. Extensive simulation study results demonstrate that, compared to other strategies, active inference generally requires far fewer iterations to identify optimal options and generally achieves superior cumulative regret, for relatively low extra computational cost.