相关论文: Reframing the Expected Free Energy: Four Formulati…

Free will is sometimes summarised in the philosophical literature as the subjective impression felt by an individual that he or she is the ultimate source or cause of his or her own choices. The two most common arguments for denying the…

With recent and rapid advancements in artificial intelligence (AI), understanding the foundation of purposeful behaviour in autonomous agents is crucial for developing safe and efficient systems. While artificial neural networks have…

This work presents a novel fault-tolerant control scheme based on active inference. Specifically, a new formulation of active inference which, unlike previous solutions, provides unbiased state estimation and simplifies the definition of…

Reinforcement Learning (RL) requires a large amount of exploration especially in sparse-reward settings. Imitation Learning (IL) can learn from expert demonstrations without exploration, but it never exceeds the expert's performance and is…

Making decisions freely presupposes that there is some indeterminacy in the environment and in the decision making engine. The former is reflected on the behavioral changes due to communicating: few changes indicate rigid environments;…

The inverse statistical problem of finding direct interactions in complex networks is difficult. In the natural sciences, well-controlled perturbation experiments are widely used to probe the structure of complex networks. However, our…

Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in the last decades. One of the central challenges of manipulation is partial observability, as the agent usually does…

The Free Energy Principle (FEP) is a theoretical framework for describing how (intelligent) systems self-organise into coherent, stable structures by minimising a free energy functional. Active Inference (AIF) is a corollary of the FEP that…

This paper considers neural representation through the lens of active inference, a normative framework for understanding brain function. It delves into how living organisms employ generative models to minimize the discrepancy between…

Computational preference elicitation methods are tools used to learn people's preferences quantitatively in a given context. Recent works on preference elicitation advocate for active learning as an efficient method to iteratively construct…

Inferring from inconsistency and making decisions are two problems which have always been treated separately by researchers in Artificial Intelligence. Consequently, different models have been proposed for each category. Different…

When a robot autonomously performs a complex task, it frequently must balance competing objectives while maintaining safety. This becomes more difficult in uncertain environments with stochastic outcomes. Enhancing transparency in the…

An inductive inference system for proving validity of formulas in the initial algebra $T_{\mathcal{E}}$ of an order-sorted equational theory $\mathcal{E}$ is presented. It has 20 inference rules, but only 9 of them require user interaction;…

We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other agent, the objective is to collect further…

Bounded rationality, that is, decision-making and planning under resource limitations, is widely regarded as an important open problem in artificial intelligence, reinforcement learning, computational neuroscience and economics. This paper…

Active inference is a mathematical framework that originated in computational neuroscience. Recently, it has been demonstrated as a promising approach for constructing goal-driven behavior in robotics. Specifically, the active inference…

This paper shows how we can combine logical representations of actions and decision theory in such a manner that seems natural for both. In particular we assume an axiomatization of the domain in terms of situation calculus, using what is…

Branching Time Active Inference (Champion et al., 2021b,a) is a framework proposing to look at planning as a form of Bayesian model expansion. Its root can be found in Active Inference (Friston et al., 2016; Da Costa et al., 2020; Champion…

In dynamic settings each economic agent's choices can be revealing of her private information. This elicitation via the rationalization of observable behavior depends each agent's perception of which payoff-relevant contingencies other…

What is the difference between goal-directed and habitual behavior? We propose a novel computational framework of decision making with Bayesian inference, in which everything is integrated as an entire neural network model. The model learns…