Related papers: Eliciting Informed Preferences

Training automated agents to complete complex tasks in interactive environments is challenging: reinforcement learning requires careful hand-engineering of reward functions, imitation learning requires specialized infrastructure and access…

A monopolistic seller aims to sell an indivisible item to multiple potential buyers. Each buyer's valuation depends on their private type and the item's quality. The seller can observe the quality but it is unknown to buyers. This quality…

Recommender systems are highly prevalent in the modern world due to their value to both users and platforms and services that employ them. Generally, they can improve the user experience and help to increase satisfaction, but they do not…

Modern recommendation systems ought to benefit by probing for and learning from delayed feedback. Research has tended to focus on learning from a user's response to a single recommendation. Such work, which leverages methods of supervised…

Reinforcement learning (RL) systems can be complex and non-interpretable, making it challenging for non-AI experts to understand or intervene in their decisions. This is due in part to the sequential nature of RL in which actions are chosen…

A monopolist seller of multiple goods screens a buyer whose type is initially unknown to both but drawn from a commonly known distribution. The buyer privately learns about his type via a signal. We derive the seller's optimal mechanism in…

We study the design of mechanisms -- e.g., auctions -- when the designer does not control information flows between mechanism participants. A mechanism equilibrium is leakage-proof if no player conditions their actions on leaked…

Reinforcement learning (RL) is inspired by the way human infants and animals learn from the environment. The setting is somewhat idealized because, in actual tasks, other agents in the environment have their own goals and behave adaptively…

Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavior. Often, this is addressed in the context of hierarchical reinforcement learning, where the aim is…

In school choice, students make decisions based on their expectations of particular schools' suitability, and the decision to gather information about schools is influenced by the acceptance odds determined by the mechanism in place. We…

We study mechanism design settings where the planner has an interest in agents receiving noisy signals about the types of other agents. We show that additional information about other agents can eliminate undesired equilibria, making it…

Algorithmic Recourse aims to provide actionable explanations, or recourse plans, to overturn potentially unfavourable decisions taken by automated machine learning models. In this paper, we propose an interaction paradigm based on a guided…

When learning is used to inform decisions about humans, such as for loans, hiring, or admissions, this can incentivize users to strategically modify their features, at a cost, to obtain positive predictions. The common assumption is that…

As we increasingly delegate important decisions to intelligent systems, it is essential that users understand how algorithmic decisions are made. Prior work has often taken a technocentric approach to transparency. In contrast, we explore…

We introduce the study of sequential information elicitation in strategic multi-agent systems. In an information elicitation setup a center attempts to compute the value of a function based on private information (a-k-a secrets) accessible…

In traditional mechanism design, agents only care about the utility they derive from the outcome of the mechanism. We look at a richer model where agents also assign non-negative dis-utility to the information about their private types…

Machine learning models are often personalized with information that is protected, sensitive, self-reported, or costly to acquire. These models use information about people but do not facilitate nor inform their consent. Individuals cannot…

In this paper we design information elicitation mechanisms for Bayesian auctions. While in Bayesian mechanism design the distributions of the players' private types are often assumed to be common knowledge, information elicitation considers…

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

Recommender systems rely heavily on the predictive accuracy of the learning algorithm. Most work on improving accuracy has focused on the learning algorithm itself. We argue that this algorithmic focus is myopic. In particular, since…