Related papers: Modeling Friends and Foes
In this paper, we consider an unconstrained distributed optimization problem over a network of agents, in which some agents are adversarial. We solve the problem via gradient-based distributed optimization algorithm and characterize the…
The aim of the strategic analysis is to (simply) carry out the game between the implementing body and possible links to the existing market situation. We are therefore playing a strategic game between us and the outside world. This…
Motivated by applications in cyber security, we develop a simple game model for describing how a learning agent's private information influences an observing agent's inference process. The model describes a situation in which one of the…
As the complexity of AI systems and their interactions with the world increases, generating explanations for their behaviour is important for safely deploying AI. For agents, the most natural abstractions for predicting behaviour attribute…
A reinforcement learning agent tries to maximize its cumulative payoff by interacting in an unknown environment. It is important for the agent to explore suboptimal actions as well as to pick actions with highest known rewards. Yet, in…
In distributed processing, agents generally collect data generated by the same underlying unknown model (represented by a vector of parameters) and then solve an estimation or inference task cooperatively. In this paper, we consider the…
We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must…
We examine the tuning of cooperative behavior in repeated multi-agent games using an analytically tractable, continuous-time, nonlinear model of opinion dynamics. Each modeled agent updates its real-valued opinion about each available…
Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly…
When humans are subject to an algorithmic decision system, they can strategically adjust their behavior accordingly (``game'' the system). While a growing line of literature on strategic classification has used game-theoretic modeling to…
Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily…
According to Dennett, the same system may be described using a `physical' (mechanical) explanatory stance, or using an `intentional' (belief- and goal-based) explanatory stance. Humans tend to find the physical stance more helpful for…
We consider any network environment in which the "best shot game" is played. This is the case where the possible actions are only two for every node (0 and 1), and the best response for a node is 1 if and only if all her neighbors play 0. A…
The goal of agents in multi-agent environments is to maximize total reward against the opposing agents that are encountered. Following a game-theoretic solution concept, such as Nash equilibrium, may obtain a strong performance in some…
In a multi-agent system, transitioning from a centralized to a distributed decision-making strategy can introduce vulnerability to adversarial manipulation. We study the potential for adversarial manipulation in a class of graphical…
The objective of this paper is to identify and analyze the response actions of a set of players embedded in sub-networks in the context of interaction and learning. We characterize strategic network formation as a static game of…
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…
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games. Combining reward randomization and policy gradient, we derive a new algorithm,…
We present an approach for systematically anticipating the actions and policies employed by \emph{oblivious} environments in concurrent stochastic games, while maximizing a reward function. Our main contribution lies in the synthesis of a…
Using mobile robots for autonomous patrolling of environments to prevent intrusions is a topic of increasing practical relevance. One of the most challenging scientific issues is the problem of finding effective patrolling strategies that,…