{"ID":2863970,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25482","arxiv_id":"2509.25482","title":"Message passing-based inference in an autoregressive active inference agent","abstract":"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 on a robot navigation task, demonstrating exploration and exploitation in a continuous-valued observation space with bounded continuous-valued actions. Compared to a classical optimal controller, the agent modulates action based on predictive uncertainty, arriving later but with a better model of the robot's dynamics.","short_abstract":"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 on a robot navigation task, demonstrating exploration and exploitation in a continuous-valued obser...","url_abs":"https://arxiv.org/abs/2509.25482","url_pdf":"https://arxiv.org/pdf/2509.25482v2","authors":"[\"Wouter M. Kouw\",\"Tim N. Nisslbeck\",\"Wouter L. N. Nuijten\"]","published":"2025-09-29T20:38:09Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\",\"cs.RO\",\"eess.SY\",\"stat.ML\"]","methods":"[\"LoRA\"]","has_code":false}