English
Related papers

Related papers: On the possibility of deep alignment

200 papers

Mutual Information between agent Actions and environment States (MIAS) quantifies the influence of agent on its environment. Recently, it was found that the maximization of MIAS can be used as an intrinsic motivation for artificial agents.…

Machine Learning · Computer Science 2020-08-04 Ruihan Zhao , Stas Tiomkin , Pieter Abbeel

This report examines what I see as the core argument for concern about existential risk from misaligned artificial intelligence. I proceed in two stages. First, I lay out a backdrop picture that informs such concern. On this picture,…

Computers and Society · Computer Science 2024-08-14 Joseph Carlsmith

Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for increasingly advanced AI systems to pose existential risks. This paper reviews the…

Computers and Society · Computer Science 2023-10-30 Rose Hadshar

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…

Artificial Intelligence · Computer Science 2023-05-09 Théophile Champion , Marek Grześ , Lisa Bonheme , Howard Bowman

Deployed, autonomous AI systems must often evaluate multiple plausible courses of action (extended sequences of behavior) in novel or under-specified contexts. Despite extensive training, these systems will inevitably encounter scenarios…

Artificial Intelligence · Computer Science 2025-11-19 Steven J. Jones , Robert E. Wray , John E. Laird

Deep reinforcement learning was instigated with the presence of trust region methods, being scalable and efficient. However, the pessimism of such algorithms, among which it forces to constrain in a trust region by all means, has been…

Machine Learning · Computer Science 2023-03-06 Jianfei Ma

This book-length article combines several peer reviewed papers and new material to analyze the issues of ethical artificial intelligence (AI). The behavior of future AI systems can be described by mathematical equations, which are adapted…

Artificial Intelligence · Computer Science 2015-11-18 Bill Hibbard

The paper describes an approach to measuring convergence of an algorithm to its result in terms of an entropy-like function of partitions of its inputs of a given length. The goal is to look at the algorithmic data processing from the…

Computational Complexity · Computer Science 2016-05-06 Anatol Slissenko

Aligning AI systems with human values remains a fundamental challenge, but does our inability to create perfectly aligned models preclude obtaining the benefits of alignment? We study a strategic setting where a human user interacts with…

Machine Learning · Computer Science 2026-02-04 Natalie Collina , Surbhi Goel , Aaron Roth , Emily Ryu , Mirah Shi

Value-alignment in normative multi-agent systems is used to promote a certain value and to ensure the consistent behaviour of agents in autonomous intelligent systems with human values. However, the current literature is limited to the…

Multiagent Systems · Computer Science 2023-10-13 Maha Riad , Vinicius de Carvalho , Fatemeh Golpayegani

We study systems of interacting reinforced stochastic processes, where agents' decisions evolve under reinforcement, network-mediated interactions, and environmental influences. In competitive environments with irreducible networks, we…

Probability · Mathematics 2025-09-18 Michele Aleandri , Paolo Dai Pra , Ida Germana Minelli

Information gathering in a partially observable environment can be formulated as a reinforcement learning (RL), problem where the reward depends on the agent's uncertainty. For example, the reward can be the negative entropy of the agent's…

Artificial Intelligence · Computer Science 2020-05-12 Yash Satsangi , Sungsu Lim , Shimon Whiteson , Frans Oliehoek , Martha White

A fundamental question in the conjunction of information theory, biophysics, bioinformatics and thermodynamics relates to the principles and processes that guide the development of natural intelligence in natural environments where…

Neural and Evolutionary Computing · Computer Science 2024-12-31 Serge Dolgikh

Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently using to understand…

Artificial Intelligence · Computer Science 2023-11-01 Sunayana Rane , Mark Ho , Ilia Sucholutsky , Thomas L. Griffiths

Reward design is a critical part of the application of reinforcement learning, the performance of which strongly depends on how well the reward signal frames the goal of the designer and how well the signal assesses progress in reaching…

Machine Learning · Computer Science 2022-08-01 Yixiang Wang , Yujing Hu , Feng Wu , Yingfeng Chen

As the complexity of AI systems and their interactions with the world increases, generating explanations for their behaviour is important for safely deploying AI. For agents, the most natural abstractions for predicting behaviour attribute…

Artificial Intelligence · Computer Science 2025-06-05 Alexis Bellot , Jonathan Richens , Tom Everitt

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an…

Machine Learning · Computer Science 2019-07-02 Kalesha Bullard , Yannick Schroecker , Sonia Chernova

When robots share the same workspace with other intelligent agents (e.g., other robots or humans), they must be able to reason about the behaviors of their neighboring agents while accomplishing the designated tasks. In practice,…

Robotics · Computer Science 2022-10-18 Junhong Xu , Durgakant Pushp , Kai Yin , Lantao Liu

The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives. However, finding such functions remains a research challenge, while in RL, setting rewards by hand is a fairly…

Artificial Intelligence · Computer Science 2023-10-10 Marcin Korecki , Damian Dailisan , Cesare Carissimo

AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a…

Artificial Intelligence · Computer Science 2023-10-06 Pei-Yu Chen , Myrthe L. Tielman , Dirk K. J. Heylen , Catholijn M. Jonker , M. Birna van Riemsdijk