paper-with-me

Papers

Coupled autoregressive active inference agents for control of multi-joint dynamical systems

2024-10-14 · Tim N. Nisslbeck, Wouter M. Kouw

We propose an active inference agent to identify and control a mechanical system with multiple bodies connected by joints. This agent is constructed from multiple scalar autoregressive model-based agents, coupled together by virtue of sharing memories. Each subagent infers parameters through Bayesian filtering and controls by minimizing expected free energy over a finite time horizon. We demonstrate that a coupled agent of this kind is able to learn the dynamics of a double mass-spring-damper system, and drive it to a desired position through a balance of explorative and exploitative actions. It outperforms the uncoupled subagents in terms of surprise and goal alignment.

📄 PDF Abstract BibTeX arXiv:2410.10415

Code (1)

biaslab/iwai2024-carxefe 공식 구현

Tasks

Position

Similar Papers 제목 키워드 기반

Multimodal VAE Active Inference Controller

2021-03-07 · Cristian Meo, Pablo Lanillos

Active inference, a theoretical construct inspired by brain processing, is a promising alternative to control artificial agents. However, current methods do not yet scale to high-dimensional inputs in continuous control.…

continuous-controlContinuous ControlRepresentation Learning

Active Inference for Physical AI Agents -- An Engineering Perspective

2026-03-21 · Bert de Vries arxiv

Physical AI agents, such as robots and other embodied systems operating under tight and fluctuating resource constraints, remain far less capable than biological agents in open-ended real-world environments. This paper a…

Message passing-based inference in an autoregressive active inference agent

2025-09-29 · Wouter M. Kouw, Tim N. Nisslbeck, Wouter L. N. Nuijten arxiv

We present the design of an autoregressive active inference agent in the form of message passing on a factor graph. Expected free energy is derived and distributed across a planning graph. The proposed agent is validated…

Robot Navigation

Structured Active Inference (Extended Abstract)

2024-06-07 · Toby St Clere Smithe

We introduce structured active inference, a large generalization and formalization of active inference using the tools of categorical systems theory. We cast generative models formally as systems "on an interface", with …

Deep Active Inference Agents for Delayed and Long-Horizon Environments

2025-05-26 · Yavar Taheri Yeganeh, Mohsen Jafari, Andrea Matta

With the recent success of world-model agents, which extend the core idea of model-based reinforcement learning by learning a differentiable model for sample-efficient control across diverse tasks, active inference (AIF)…

Model-based Reinforcement Learning