Related papers: Multi-Modal and Multi-Factor Branching Time Active…
We develop an active inference route-planning method for the autonomous control of intelligent agents. The aim is to reconnoiter a geographical area to maintain a common operational picture. To achieve this, we construct an evidence map…
In many scientific and engineering fields, where acquiring high-quality data is expensive--such as medical imaging, environmental monitoring, and remote sensing--strategic sampling of unobserved regions based on prior observations is…
Modern logical reasoning with LLMs primarily relies on employing complex interactive frameworks that decompose the reasoning process into subtasks solved through carefully designed prompts or requiring external resources (e.g., symbolic…
Intelligent agents must pursue their goals in complex environments with partial information and often limited computational capacity. Reinforcement learning methods have achieved great success by creating agents that optimize engineered…
Given the rapid advancement of artificial intelligence, understanding the foundations of intelligent behaviour is increasingly important. Active inference, regarded as a general theory of behaviour, offers a principled approach to probing…
Active inference is a theory of perception, learning and decision making, which can be applied to neuroscience, robotics, and machine learning. Recently, reasearch has been taking place to scale up this framework using Monte-Carlo tree…
We introduce a Bayesian active learning algorithm that efficiently elucidates phase diagrams. Using a novel acquisition function that assesses both the impact and likelihood of the next observation, the algorithm iteratively determines the…
In forecasting problems it is important to know whether or not recent events represent a regime change (low long-term predictive potential), or rather a local manifestation of longer term effects (potentially higher predictive potential).…
Black-box AI (BBAI) systems such as foundational models are increasingly being used for sequential decision making. To ensure that such systems are safe to operate and deploy, it is imperative to develop efficient methods that can provide a…
Imitation learning is a class of promising policy learning algorithms that is free from many practical issues with reinforcement learning, such as the reward design issue and the exploration hardness. However, the current imitation…
Inference and decision making under uncertainty are key processes in every autonomous system and numerous robotic problems. In recent years, the similarities between inference and decision making triggered much work, from developing unified…
Finding an appropriate representation of dynamic activities in the brain is crucial for many downstream applications. Due to its highly dynamic nature, temporally averaged fMRI (functional magnetic resonance imaging) can only provide a…
Task and Motion Planning (TAMP) has made strides in complex manipulation tasks, yet the execution robustness of the planned solutions remains overlooked. In this work, we propose a method for reactive TAMP to cope with runtime uncertainties…
The Bradley-Terry model is a popular approach to describe probabilities of the possible outcomes when elements of a set are repeatedly compared with one another in pairs. It has found many applications including animal behaviour, chess…
We revisit the Bayesian Context Trees (BCT) modelling framework for discrete time series, which was recently found to be very effective in numerous tasks including model selection, estimation and prediction. A novel representation of the…
Forecasting Multivariate Time Series (MTS) involves significant challenges in various application domains. One immediate challenge is modeling temporal patterns with the finite length of the input. These temporal patterns usually involve…
Bayesian matrix factorization (BMF) is a powerful tool for producing low-rank representations of matrices and for predicting missing values and providing confidence intervals. Scaling up the posterior inference for massive-scale matrices is…
We present a method for active inference with partial observations in stochastic systems through incentive design, also known as the leader-follower game. Consider a leader agent who aims to infer a follower agent's type given a finite set…
Active inference is a mathematical framework for understanding how agents (biological or artificial) interact with their environments, enabling continual adaptation and decision-making. It combines Bayesian inference and free energy…
Recent advances demonstrate that increasing inference-time computation can significantly boost the reasoning capabilities of large language models (LLMs). Although repeated sampling (i.e., generating multiple candidate outputs) is a highly…