相关论文: A Minimal Active Inference Agent

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Bias exists in how we pick leaders, who we perceive as being influential, and who we interact with, not only in society, but in organizational contexts. Drawing from leadership emergence and social influence theories, we investigate…

We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning. The agent uses a bottleneck mechanism over a set-based representation to force the number of…

We present some arguments why existing methods for representing agents fall short in applications crucial to artificial life. Using a thought experiment involving a fictitious dynamical systems model of the biosphere we argue that the…

In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations. In this manuscript we focus on predictions expressed as General Value Functions:…

To handle unintended changes in the environment by agents, we propose an environment-centric active inference EC-AIF in which the Markov Blanket of active inference is defined starting from the environment. In normal active inference, the…

Training sophisticated agents for optimal decision-making under uncertainty has been key to the rapid development of modern autonomous systems across fields. Notably, model-free reinforcement learning (RL) has enabled decision-making agents…

In this work, we introduce a new framework for active experimentation, the Prediction-Guided Active Experiment (PGAE), which leverages predictions from an existing machine learning model to guide sampling and experimentation. Specifically,…

We consider a network of agents that aim to learn some unknown state of the world using private observations and exchange of beliefs. At each time, agents observe private signals generated based on the true unknown state. Each agent might…

Active Learning (AL) is increasingly important in a broad range of applications. Two main AL principles to obtain accurate classification with few labeled data are refinement of the current decision boundary and exploration of poorly…

In this paper, we describe an integrated framework for autonomous decision making in a dynamic and interactive environment. We model the interactions between the ego agent and its operating environment as a two-player dynamic game, and…

Although research has produced promising results demonstrating the utility of active inference (AIF) in Markov decision processes (MDPs), there is relatively less work that builds AIF models in the context of environments and problems that…

Active inference (AIF) unifies exploration and exploitation by minimizing the Expected Free Energy (EFE), balancing epistemic value (information gain) and pragmatic value (task performance) through a curiosity coefficient. Yet it has been…

The free energy principle has been proposed as a unifying account of brain function. It is closely related, and in some cases subsumes, earlier unifying ideas such as Bayesian inference, predictive coding, and active learning. This article…

Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. As an everlasting challenge for machine learning, in many…

Growing concerns regarding the operational usage of AI models in the real-world has caused a surge of interest in explaining AI models' decisions to humans. Reinforcement Learning is not an exception in this regard. In this work, we propose…

Agents are a special kind of AI-based software in that they interact in complex environments and have increased potential for emergent behaviour. Explaining such emergent behaviour is key to deploying trustworthy AI, but the increasing…

I study a principal-agent model in which a principal hires an agent to collect information about an unknown continuous state. The agent acquires a signal whose distribution is centered around the state, controlling the signal's precision at…

Modern AI systems increasingly operate inside markets and institutions where data, behavior, and incentives are endogenous. This paper develops an economic foundation for multi-agent learning by studying a principal-agent interaction in a…

By dynamic planning, we refer to the ability of the human brain to infer and impose motor trajectories related to cognitive decisions. A recent paradigm, active inference, brings fundamental insights into the adaptation of biological…