Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network

TL;DR

This paper introduces a variational recurrent neural network framework based on active inference and predictive coding, enabling habituated agents to generate goal-directed action plans with better generalization from limited data.

Contribution

It proposes a novel model combining active inference and variational recurrent neural networks to improve goal-directed planning and generalization in robotic agents.

Findings

The model outperforms conventional forward models in goal-directed planning.

It achieves effective learning and planning with limited training data.

The learned prior constrains motor plan search within habituated trajectories.

Abstract

It is crucial to ask how agents can achieve goals by generating action plans using only partial models of the world acquired through habituated sensory-motor experiences. Although many existing robotics studies use a forward model framework, there are generalization issues with high degrees of freedom. The current study shows that the predictive coding (PC) and active inference (AIF) frameworks, which employ a generative model, can develop better generalization by learning a prior distribution in a low dimensional latent state space representing probabilistic structures extracted from well habituated sensory-motor trajectories. In our proposed model, learning is carried out by inferring optimal latent variables as well as synaptic weights for maximizing the evidence lower bound, while goal-directed planning is accomplished by inferring latent variables for maximizing the estimated lower bound. Our proposed model was evaluated with both simple and complex robotic tasks in simulation, which demonstrated sufficient generalization in learning with limited training data by setting an intermediate value for a regularization coefficient. Furthermore, comparative simulation results show that the proposed model outperforms a conventional forward model in goal-directed planning, due to the learned prior confining the search of motor plans within the range of habituated trajectories.