English
Related papers

Related papers: Universal AI maximizes Variational Empowerment

200 papers

The development of artificial intelligence systems is transitioning from creating static, task-specific models to dynamic, agent-based systems capable of performing well in a wide range of applications. We propose an Interactive Agent…

Inspired by recent progress in multi-agent Reinforcement Learning (RL), in this work we examine the collective intelligent behaviour of theoretical universal agents by introducing a weighted mixture operation. Given a weighted set of…

Artificial Intelligence · Computer Science 2023-02-14 Samuel Allen Alexander , David Quarel , Len Du , Marcus Hutter

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…

Machine Learning · Computer Science 2024-12-24 Akane Tsuboya , Yu Kono , Tatsuji Takahashi

The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward…

Interactive Artificial Intelligence (AI) agents are becoming increasingly prevalent in society. However, application of such systems without understanding them can be problematic. Black-box AI systems can lead to liability and…

Computers and Society · Computer Science 2023-01-16 Pradyumna Tambwekar , Matthew Gombolay

Agents of general intelligence deployed in real-world scenarios must adapt to ever-changing environmental conditions. While such adaptive agents may leverage engineered knowledge, they will require the capacity to construct and evaluate…

Artificial Intelligence · Computer Science 2016-06-20 Craig Sherstan , Adam White , Marlos C. Machado , Patrick M. Pilarski

As Large Language Models (LLM) based multi-agent systems become increasingly prevalent, the collective behaviors, e.g., collective intelligence, of such artificial communities have drawn growing attention. This work aims to answer a…

Artificial Intelligence · Computer Science 2025-12-12 Muhua Huang , Qinlin Zhao , Xiaoyuan Yi , Xing Xie

We propose a practical integration of logical state abstraction with AIXI, a Bayesian optimality notion for reinforcement learning agents, to significantly expand the model class that AIXI agents can be approximated over to complex…

Artificial Intelligence · Computer Science 2022-10-14 Samuel Yang-Zhao , Tianyu Wang , Kee Siong Ng

An artificial general intelligence (AGI) might have an instrumental drive to modify its utility function to improve its ability to cooperate, bargain, promise, threaten, and resist and engage in blackmail. Such an AGI would necessarily have…

General Finance · Quantitative Finance 2020-03-03 James D. Miller , Roman Yampolskiy , Olle Häggström

We consider a ubiquitous scenario in the Internet economy when individual decision-makers (henceforth, agents) both produce and consume information as they make strategic choices in an uncertain environment. This creates a three-way…

Computer Science and Game Theory · Computer Science 2021-04-09 Yishay Mansour , Aleksandrs Slivkins , Vasilis Syrgkanis , Zhiwei Steven Wu

Agentic AI seeks to endow systems with sustained autonomy, reasoning, and interaction capabilities. To realize this vision, its assumptions about agency must be complemented by explicit models of cognition, cooperation, and governance. This…

Artificial Intelligence · Computer Science 2026-02-11 Virginia Dignum , Frank Dignum

As Artificial Intelligence (AI) systems continue to grow in size and complexity, so does the difficulty of the quest for AI transparency. In a world of large models and complex AI systems, why do we explain AI and what should we explain?…

Artificial Intelligence · Computer Science 2026-04-23 Karina Cortinas-Lorenzo , Gavin Doherty

The fact that accurately predicted information can serve as an energy source paves the way for new approaches to autonomous learning. The energy derived from a sequence of successful predictions can be recycled as an immediate incentive and…

Emerging Technologies · Computer Science 2024-07-09 Alex Ushveridze

Reinforcement learners can attain high reward through novel unintended strategies. We study a Bayesian mitigation for general environments: we expand the agent's subjective reward range to include a large negative value $-L$, while the true…

Machine Learning · Computer Science 2026-04-16 Aram Ebtekar , Michael K. Cohen

Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation. In parallel, the long-standing notion of AI agents, defined by the sensing-decision-action…

Machine Learning · Computer Science 2025-10-02 Sicong Liu , Weiye Wu , Xiangrui Xu , Teng Li , Bowen Pang , Bin Guo , Zhiwen Yu

Humans can often predict physical outcomes after only a few observations, a capability known as physical intuition. The mechanisms underlying this efficient learning remain elusive. Here, we introduce a variational learning framework in…

Computational Physics · Physics 2026-03-19 Jingruo Peng , Shuze Zhu

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…

Machine Learning · Computer Science 2019-02-26 Ahmed H. Qureshi , Byron Boots , Michael C. Yip

$\textit{Embedded agents}$ are not explicitly separated from their environment, lacking clear I/O channels. Such agents can reason about and modify their internal parts, which they are incentivized to shortcut or $\textit{wirehead}$ in…

Artificial Intelligence · Computer Science 2019-06-24 Arushi Majha , Sayan Sarkar , Davide Zagami

Multi-agent reinforcement learning (MARL) requires agents to explore within a vast joint action space to find joint actions that lead to coordination. Existing value-based MARL algorithms commonly rely on random exploration, such as…

Multiagent Systems · Computer Science 2025-02-10 Lukas Schäfer , Oliver Slumbers , Stephen McAleer , Yali Du , Stefano V. Albrecht , David Mguni

In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. Existing AutoGPT-style techniques have inherent limitations, such as a heavy reliance on precise descriptions for…