Related papers: Personalized Help for Optimizing Low-Skilled Users…

To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach to specifying complex goals asks humans to judge during training which agent behaviors are safe and…

LLMs promise to assist humans -- not just by answering questions, but by offering useful guidance across a wide range of tasks. But how far does that assistance go? Can a large language model based agent actually help someone accomplish…

Many real-world games contain parameters which can affect payoffs, action spaces, and information states. For fixed values of the parameters, the game can be solved using standard algorithms. However, in many settings agents must act…

Online information ecosystems are now central to our everyday social interactions. Of the many opportunities and challenges this presents, the capacity for artificial agents to shape individual and collective human decision-making in such…

This paper reviews an experiment in human-computer interaction, where interaction takes place when humans attempt to teach a computer to play a strategy board game. We show that while individually learned models can be shown to improve the…

In this paper I present several algorithmic techniques for improving the decision process of multiple types of agents behaving in environments where their interests are in conflict. The interactions between the agents are modelled by using…

In this paper, we present the strategy of Agent Madoff, which is a heuristic-based negotiation agent that won 2nd place at the Automated Negotiating Agents Competition (ANAC 2017). Agent Madoff is implemented to play the game Diplomacy,…

People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at learning such tasks. Thus, there is an opportunity for AI…

Agentic AI is shifting the cybersecurity landscape as attackers and defenders leverage AI agents to augment humans and automate common tasks. In this article, we examine the implications for cyber warfare and global politics as Agentic AI…

The rapid rise of large language models (LLMs) has shifted artificial intelligence (AI) research toward agentic systems, motivating the use of weaker and more flexible notions of agency. However, this shift raises key questions about the…

Historically, much research and development in human computer interaction has focused on atomic and generalizable tasks, where task completion time indicates productivity. However, the emergence of competitive games and esports reminds us…

Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects…

To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of…

We consider the task of building strong but human-like policies in multi-agent decision-making problems, given examples of human behavior. Imitation learning is effective at predicting human actions but may not match the strength of expert…

The field of collective intelligence studies how teams can achieve better results than any of the team members alone. The special case of human-machine teams carries unique challenges in this regard. For example, human teams often achieve…

Humans use language to accomplish a wide variety of tasks - asking for and giving advice being one of them. In online advice forums, advice is mixed in with non-advice, like emotional support, and is sometimes stated explicitly, sometimes…

Strategic decision-making requires balancing immediate opportunities against long-term objectives: a tension fundamental to competitive environments. We investigate this trade-off in chess by analyzing the dynamics of human and AI gameplay…

We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies against it, achieving a >97% win rate against KataGo running at superhuman settings. Our adversaries do not win by playing Go well. Instead, they…

We consider the problem of creating assistants that can help agents solve new sequential decision problems, assuming the agent is not able to specify the reward function explicitly to the assistant. Instead of acting in place of the agent…

For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want. In this paper we discuss some behavioural issues for language agents, arising from accidental misspecification by…