Related papers: Estimating and Incentivizing Imperfect-Knowledge A…
Multi-armed bandits (MAB) model sequential decision making problems, in which a learner sequentially chooses arms with unknown reward distributions in order to maximize its cumulative reward. Most of the prior work on MAB assumes that the…
Online platforms in the Internet Economy commonly incorporate recommender systems that recommend products (or "arms") to users (or "agents"). A key challenge in this domain arises from myopic agents who are naturally incentivized to exploit…
Models of economic decision makers often include idealized assumptions, such as rationality, perfect foresight, and access to all relevant pieces of information. These assumptions often assure the models' internal validity, but, at the same…
We study the stochastic multi-armed bandit (MAB) problem in the presence of side-observations across actions that occur as a result of an underlying network structure. In our model, a bipartite graph captures the relationship between…
In a multi-armed bandit (MAB) problem a gambler needs to choose at each round of play one of K arms, each characterized by an unknown reward distribution. Reward realizations are only observed when an arm is selected, and the gambler's…
We initiate the study of a repeated principal-agent problem over a finite horizon $T$, where a principal sequentially interacts with $K\geq 2$ types of agents arriving in an adversarial order. At each round, the principal strategically…
The classical multi-armed bandit (MAB) problem involves a learner and a collection of K independent arms, each with its own ex ante unknown independent reward distribution. At each one of a finite number of rounds, the learner selects one…
Modern AI systems increasingly operate inside markets and institutions where data, behavior, and incentives are endogenous. This paper develops an economic foundation for multi-agent learning by studying a principal-agent interaction in a…
When a reinforcement learning (RL) method has to decide between several optional policies by solely looking at the received reward, it has to implicitly optimize a Multi-Armed-Bandit (MAB) problem. This arises the question: are current RL…
We study collaborative learning in multi-agent Bayesian bandit problems, where strategic agents collectively solve the same bandit instance. While multiple agents can accelerate learning by sharing information, strategic agents might prefer…
Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement…
How to incentivize self-interested agents to explore when they prefer to exploit? Consider a population of self-interested agents that make decisions under uncertainty. They "explore" to acquire new information and "exploit" this…
Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown…
The multi-armed bandit (MAB) model is one of the most classical models to study decision-making in an uncertain environment. In this model, a player chooses one of $K$ possible arms of a bandit machine to play at each time step, where the…
Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental…
We study principal-agent problems where a farsighted agent takes costly actions in an MDP. The core challenge in these settings is that agent's actions are hidden to the principal, who can only observe their outcomes, namely state…
The multi-armed bandit (MAB) problem is an active learning framework that aims to select the best among a set of actions by sequentially observing rewards. Recently, it has become popular for a number of applications over wireless networks,…
Designing a distribution of environments in which RL agents can learn interesting and useful skills is a challenging and poorly understood task, for multi-agent environments the difficulties are only exacerbated. One approach is to train a…
In many scenarios, a principal dynamically interacts with an agent and offers a sequence of incentives to align the agent's behavior with a desired objective. This paper focuses on the problem of synthesizing an incentive sequence that,…
We introduce a framework for decentralized online learning for multi-armed bandits (MAB) with multiple cooperative players. The reward obtained by the players in each round depends on the actions taken by all the players. It's a team…