English
Related papers

Related papers: Settling the Reward Hypothesis

200 papers

We present a one-fits-all programmatic approach to reason about a plethora of objectives on probabilistic programs. The first ingredient is to add a reward-statement to the language. We then define a program transformation applying a…

Programming Languages · Computer Science 2026-03-04 Philipp Schröer , Joost-Pieter Katoen

The paper proposes a fresh look at the concept of goal and advances that motivational attitudes like desire, goal and intention are just facets of the broader notion of (acceptable) outcome. We propose to encode the preferences of an agent…

Logic in Computer Science · Computer Science 2022-09-13 Guido Governatori , Francesco Olivieri , Simone Scannapieco , Antonino Rotolo , Matteo Cristani

Two core challenges of alignment are 1) scalable oversight and 2) accounting for the dynamic nature of human values. While solutions like recursive reward modeling address 1), they do not simultaneously account for 2). We sketch a roadmap…

Artificial Intelligence · Computer Science 2025-03-19 Florian Mai , David Kaczér , Nicholas Kluge Corrêa , Lucie Flek

Goals express agents' intentions and allow them to organize their behavior based on low-dimensional abstractions of high-dimensional world states. How can agents develop such goals autonomously? This paper proposes a detailed conceptual and…

Machine Learning · Computer Science 2014-10-22 Matthias Rolf , Minoru Asada

It is often argued that one goal of explaining automated decision systems (ADS) is to facilitate positive perceptions (e.g., fairness or trustworthiness) of users towards such systems. This viewpoint, however, makes the implicit assumption…

Human-Computer Interaction · Computer Science 2021-08-17 Jakob Schoeffer , Niklas Kuehl

Reinforcement learning problems are often described through rewards that indicate if an agent has completed some task. This specification can yield desirable behavior, however many problems are difficult to specify in this manner, as one…

Artificial Intelligence · Computer Science 2016-08-15 Ashley Edwards , Charles Isbell , Atsuo Takanishi

Reward is the driving force for reinforcement-learning agents. This paper is dedicated to understanding the expressivity of reward as a way to capture tasks that we would want an agent to perform. We frame this study around three new…

Machine Learning · Computer Science 2022-01-19 David Abel , Will Dabney , Anna Harutyunyan , Mark K. Ho , Michael L. Littman , Doina Precup , Satinder Singh

Can humans get arbitrarily capable reinforcement learning (RL) agents to do their bidding? Or will sufficiently capable RL agents always find ways to bypass their intended objectives by shortcutting their reward signal? This question…

Artificial Intelligence · Computer Science 2021-03-29 Tom Everitt , Marcus Hutter , Ramana Kumar , Victoria Krakovna

We propose a new determinacy hypothesis for transfinite games, use the hypothesis to extend the perfect set theorem, prove relationships between various determinacy hypotheses, expose inconsistent versions of determinacy, and provide a…

Logic · Mathematics 2016-12-16 Dmytro Taranovsky

Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is…

Machine Learning · Computer Science 2025-05-30 Chaoqi Wang , Zhuokai Zhao , Yibo Jiang , Zhaorun Chen , Chen Zhu , Yuxin Chen , Jiayi Liu , Lizhu Zhang , Xiangjun Fan , Hao Ma , Sinong Wang

In this paper, we build a new test of rational expectations based on the marginal distributions of realizations and subjective beliefs. This test is widely applicable, including in the common situation where realizations and beliefs are…

Econometrics · Economics 2023-04-18 Xavier D'Haultfoeuille , Christophe Gaillac , Arnaud Maurel

Many definitions of business processes refer to business goals, value creation, or profits/gains of sorts. Nevertheless, the focus of formal methods research on business processes, like the well-known soundness property, lies on correctness…

Computer Science and Game Theory · Computer Science 2020-06-12 Tobias Heindel , Ingo Weber

Score matching is a recently developed parameter learning method that is particularly effective to complicated high dimensional density models with intractable partition functions. In this paper, we study two issues that have not been…

Machine Learning · Computer Science 2012-05-14 Siwei Lyu

We present a framework for designing scores to summarize performance metrics. Our design has two multi-criteria objectives: (1) improving on scores should improve all performance metrics, and (2) achieving pareto-optimal scores should…

Computers and Society · Computer Science 2024-10-10 Anmol Kabra , Mina Karzand , Tosca Lechner , Nathan Srebro , Serena Wang

In this paper, we propose DuaShepherd, a novel reward modeling framework that integrates two complementary reward signals, correctness and potential, to enhance the mathematical reasoning capabilities of Large Language Models (LLMs). While…

Computation and Language · Computer Science 2025-06-24 Yuanhao Wu , Juntong Song , Hanning Zhang , Tong Zhang , Cheng Niu

We consider a setting where in a known future time, a certain continuous random variable will be realized. There is a public prediction that gradually converges to its realized value, and an expert that has access to a more accurate…

Computer Science and Game Theory · Computer Science 2016-05-25 Amir Ban , Yossi Azar , Yishay Mansour

Aligning multimodal large language models (MLLMs) with human preferences often relies on single-signal, model-based reward methods. Such monolithic rewards often lack confidence calibration across domain-specific tasks, fail to capture…

Artificial Intelligence · Computer Science 2025-10-08 Radha Gulhane , Sathish Reddy Indurthi

We provide an original theoretical study of Inverse Reinforcement Learning (IRL) through the lens of reward compatibility, a novel framework to quantify the compatibility of a reward with the given expert's demonstrations. Intuitively, a…

Machine Learning · Computer Science 2025-01-15 Filippo Lazzati , Mirco Mutti , Alberto Metelli

Reward machines (RMs) are a recent formalism for representing the reward function of a reinforcement learning task through a finite-state machine whose edges encode subgoals of the task using high-level events. The structure of RMs enables…

Machine Learning · Computer Science 2023-06-06 Daniel Furelos-Blanco , Mark Law , Anders Jonsson , Krysia Broda , Alessandra Russo

People are remarkably capable of generating their own goals, beginning with child's play and continuing into adulthood. Despite considerable empirical and computational work on goals and goal-oriented behavior, models are still far from…

Artificial Intelligence · Computer Science 2025-05-20 Guy Davidson , Graham Todd , Julian Togelius , Todd M. Gureckis , Brenden M. Lake