Prior Preference Learning from Experts:Designing a Reward with Active Inference

TL;DR

This paper bridges active inference and reinforcement learning by interpreting expected free energy as a value function, proposing a method to learn prior preferences from experts, and demonstrating its application to inverse reinforcement learning.

Contribution

It introduces a novel perspective connecting active inference with RL, extending EFE as a reward signal, and proposes a new method for learning prior preferences from expert demonstrations.

Findings

EFE can be treated as a negative value function.

Active inference can be applied to inverse RL.

Experimental results support the feasibility of EFE-based rewards.

Abstract

Active inference may be defined as Bayesian modeling of a brain with a biologically plausible model of the agent. Its primary idea relies on the free energy principle and the prior preference of the agent. An agent will choose an action that leads to its prior preference for a future observation. In this paper, we claim that active inference can be interpreted using reinforcement learning (RL) algorithms and find a theoretical connection between them. We extend the concept of expected free energy (EFE), which is a core quantity in active inference, and claim that EFE can be treated as a negative value function. Motivated by the concept of prior preference and a theoretical connection, we propose a simple but novel method for learning a prior preference from experts. This illustrates that the problem with inverse RL can be approached with a new perspective of active inference. Experimental results of prior preference learning show the possibility of active inference with EFE-based rewards and its application to an inverse RL problem.