Related papers: Aligning AI Agents via Information-Directed Sampli…

Conducting randomized experiments in education settings raises the question of how we can use machine learning techniques to improve educational interventions. Using Multi-Armed Bandits (MAB) algorithms like Thompson Sampling (TS) in…

We study the repeated principal-agent bandit game, where the principal indirectly interacts with the unknown environment by proposing incentives for the agent to play arms. Most existing work assumes the agent has full knowledge of the…

Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement. However, such algorithms usually…

Advanced AI systems sometimes act in ways that differ from human intent. To gather clear, reproducible examples, we ran the Misalignment Bounty: a crowdsourced project that collected cases of agents pursuing unintended or unsafe goals. The…

Value alignment has emerged in recent years as a basic principle to produce beneficial and mindful Artificial Intelligence systems. It mainly states that autonomous entities should behave in a way that is aligned with our human values. In…

As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for acceptable behavior…

A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to…

We consider the Max $K$-Armed Bandit problem, where a learning agent is faced with several stochastic arms, each a source of i.i.d. rewards of unknown distribution. At each time step the agent chooses an arm, and observes the reward of the…

The multi-armed bandit problem is a core framework for sequential decision-making under uncertainty, but classical algorithms often fail in environments with hidden, time-varying states that confound reward estimation and optimal action…

Information is often stored in a distributed and proprietary form, and agents who own information are often self-interested and require incentives to reveal their information. Suitable mechanisms are required to elicit and aggregate such…

Many real-world functions are defined over both categorical and category-specific continuous variables and thus cannot be optimized by traditional Bayesian optimization (BO) methods. To optimize such functions, we propose a new method that…

AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…

This paper introduces a general multi-agent bandit model in which each agent is facing a finite set of arms and may communicate with other agents through a central controller in order to identify, in pure exploration, or play, in regret…

We study here the problem of learning the exploration exploitation trade-off in the contextual bandit problem with linear reward function setting. In the traditional algorithms that solve the contextual bandit problem, the exploration is a…

It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that…

Balancing game difficulty in video games is a key task to create interesting gaming experiences for players. Mismatching the game difficulty and a player's skill or commitment results in frustration or boredom on the player's side, and…

Time-inconsistency is a characteristic of human behavior in which people plan for long-term benefits but take actions that differ from the plan due to conflicts with short-term benefits. Such time-inconsistent behavior is believed to be…

AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business…

Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better…

Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel…