Reactive Environments for Active Inference Agents with RxEnvironments.jl

TL;DR

This paper introduces Reactive Environments, a new paradigm and Julia package for modeling complex multi-agent interactions and communication within active inference frameworks, enhancing environmental modeling beyond traditional reinforcement learning approaches.

Contribution

The paper presents Reactive Environments as a novel paradigm and implements it in RxEnvironments.jl, enabling complex multi-agent communication and interactions in active inference systems.

Findings

Demonstrates the flexibility of Reactive Environments through multiple complex case studies.

Shows improved modeling of multi-agent communication and interactions.

Provides an efficient implementation using Reactive Programming in Julia.

Abstract

Active Inference is a framework that emphasizes the interaction between agents and their environment. While the framework has seen significant advancements in the development of agents, the environmental models are often borrowed from reinforcement learning problems, which may not fully capture the complexity of multi-agent interactions or allow complex, conditional communication. This paper introduces Reactive Environments, a comprehensive paradigm that facilitates complex multi-agent communication. In this paradigm, both agents and environments are defined as entities encapsulated by boundaries with interfaces. This setup facilitates a robust framework for communication in nonequilibrium-Steady-State systems, allowing for complex interactions and information exchange. We present a Julia package RxEnvironments.jl, which is a specific implementation of Reactive Environments, where we utilize a Reactive Programming style for efficient implementation. The flexibility of this paradigm is demonstrated through its application to several complex, multi-agent environments. These case studies highlight the potential of Reactive Environments in modeling sophisticated systems of interacting agents.