English
Related papers

Related papers: 'Indifference' methods for managing agent rewards

200 papers

Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When designing the reward, we might think of some specific training…

Artificial Intelligence · Computer Science 2020-10-08 Dylan Hadfield-Menell , Smitha Milli , Pieter Abbeel , Stuart Russell , Anca Dragan

We introduce three concepts that describe an agent's incentives: response incentives indicate which variables in the environment, such as sensitive demographic information, affect the decision under the optimal policy. Instrumental control…

Artificial Intelligence · Computer Science 2025-06-24 Ryan Carey , Eric Langlois , Chris van Merwijk , Shane Legg , Tom Everitt

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

Machine Learning · Computer Science 2018-11-29 David Warde-Farley , Tom Van de Wiele , Tejas Kulkarni , Catalin Ionescu , Steven Hansen , Volodymyr Mnih

To learn directed behaviors in complex environments, intelligent agents need to optimize objective functions. Various objectives are known for designing artificial agents, including task rewards and intrinsic motivation. However, it is…

Artificial Intelligence · Computer Science 2022-02-15 Danijar Hafner , Pedro A. Ortega , Jimmy Ba , Thomas Parr , Karl Friston , Nicolas Heess

We consider the design of experiments to evaluate treatments that are administered by self-interested agents, each seeking to achieve the highest evaluation and win the experiment. For example, in an advertising experiment, a company wishes…

Methodology · Statistics 2015-09-18 Panos Toulis , David C. Parkes , Elery Pfeffer , James Zou

Human interactions are influenced by emotions, temperament, and affection, often conflicting with individuals' underlying preferences. Without explicit knowledge of those preferences, judging whether behaviour is appropriate becomes…

Computer Science and Game Theory · Computer Science 2025-11-05 Victor Villin , Christos Dimitrakakis

Difference-in-differences is one of the most used identification strategies in empirical work in economics. This chapter reviews a number of important, recent developments related to difference-in-differences. First, this chapter reviews…

Econometrics · Economics 2022-08-02 Brantly Callaway

Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated…

Artificial Intelligence · Computer Science 2024-11-07 Erik M. Lintunen , Nadia M. Ady , Christian Guckelsberger

Motivated by the control theoretic distinction between controllable and uncontrollable events, we distinguish between two types of agents within a multi-agent system: controllable agents, which are directly controlled by the system's…

Artificial Intelligence · Computer Science 2014-11-17 R. I. Brafman , M. Tennenholtz

Designing reward functions is difficult: the designer has to specify what to do (what it means to complete the task) as well as what not to do (side effects that should be avoided while completing the task). To alleviate the burden on the…

Machine Learning · Computer Science 2020-10-16 Victoria Krakovna , Laurent Orseau , Richard Ngo , Miljan Martic , Shane Legg

In competitive games, it is common to assign each player a real number rating signifying their skill level. A rating system is a procedure by which player ratings are adjusted upwards each time they win, or downwards each time they lose.…

Data Structures and Algorithms · Computer Science 2024-07-17 Greg Bodwin , Forest Zhang

Preserving the privacy of preferences (or rewards) of a sequential decision-making agent when decisions are observable is crucial in many physical and cybersecurity domains. For instance, in wildlife monitoring, agents must allocate…

Artificial Intelligence · Computer Science 2024-07-16 Shashank Reddy Chirra , Pradeep Varakantham , Praveen Paruchuri

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Machine Learning · Computer Science 2019-06-25 Rohin Shah , Noah Gundotra , Pieter Abbeel , Anca D. Dragan

Multi-agent reinforcement learning in mixed-motive settings presents a fundamental challenge: agents must balance individual interests with collective goals, which are neither fully aligned nor strictly opposed. To address this, reward…

Multiagent Systems · Computer Science 2025-08-26 Woojun Kim , Katia Sycara

When allocating indivisible items, there are various ways to use monetary transfers for eliminating envy. Particularly, one can apply a balanced vector of transfer payments, or charge each agent a positive amount, or -- contrarily -- give…

Computer Science and Game Theory · Computer Science 2025-06-24 Noga Klein Elmalem , Rica Gonen , Erel Segal-Halevi

In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting…

Artificial Intelligence · Computer Science 2021-12-20 Jasmina Gajcin , Rahul Nair , Tejaswini Pedapati , Radu Marinescu , Elizabeth Daly , Ivana Dusparic

How do incentive levels affect strategic behaviour? We address this with an experiment that separately identifies own- and opponent-incentive effects in two dominance-solvable games that differ in strategic complexity. Higher own incentives…

Theoretical Economics · Economics 2026-03-30 Teresa Esteban-Casanelles , Duarte Gonçalves

We study the design of effort-maximizing grading schemes between agents with private abilities. Assuming agents derive value from the information their grade reveals about their ability, we find that more informative grading schemes induce…

Computer Science and Game Theory · Computer Science 2024-11-11 Sumit Goel

Incentives play an important role in (security and IT) risk management of a large-scale organization with multiple autonomous divisions. This paper presents an incentive mechanism design framework for risk management based on a…

Computer Science and Game Theory · Computer Science 2010-12-16 Tansu Alpcan

Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key challenge, however, that is not addressed by many of these methods is multi-agent credit assignment: assessing…

Multiagent Systems · Computer Science 2024-12-20 Jacopo Castellini , Sam Devlin , Frans A. Oliehoek , Rahul Savani
‹ Prev 1 2 3 10 Next ›