The generality of decision and game theory has enabled domain-independent progress in AI research. For example, a better algorithm for finding good policies in (PO)MDPs can be instantly used in a variety of applications. But such a general theory is lacking when it comes to moral decision making. For AI applications with a moral component, are we then forced to build systems based on many ad-hoc rules? In this paper we discuss possible ways to avoid this conclusion.

We study the Stable Invitations Problem (SIP) in which an event organizer is to invite a subset of agents (from a group of agents) to an event, subject to certain rationality criteria. In SIP, the agents have friends, enemies, and preferences on the number of attendees at the event; an agent is willing to attend the event if all friends of the agent attend, no enemy of the agent attends, and the number of attendees is acceptable to the agent. We consider two solution concepts: (1) individual rationality (everyone who is invited is willing to attend) and (2) (Nash) stability (no agent wants to deviate from the given invitation).It is known that finding an invitation of given size for either concept is NP-complete. In this work, we study the complexity of SIP on a finer scale, through the lense of parameterized complexity.For the two solution concepts and the special cases where the number of friends and/or enemies is bounded above by a constant, we show that the problems belong to different complexity classes when parameterized by the size of solutions.For instance finding an individually rational invitation of size k is W[1]-complete, yet finding a stable invitation is W[2]-complete.Moreover, when all friend and enemy relations are symmetric, finding a solution of either of the concepts becomes fixed-parameter tractable unless agents have unbounded number(s) of enemies.

Self-awareness is a crucial feature for a sociable agent or robot to better interact with humans. In a futuristic scenario, a conversational agent may occasionally be asked for its own opinion or suggestion based on its own thought, feelings, or experiences as if it is an individual with identity, personality, and social life. In moving towards that direction, in this paper, a brain inspired model of self-awareness is presented that allows an agent to learn to attend to different aspects of self as an individual with identity, physical embodiment, mental states, experiences, and reflections on how others may think about oneself. The model is built and realized on a NAO humanoid robotic platform to investigate the role of this capacity of self-awareness on the robot's learning and interactivity.

The annual International Automated Negotiating Agents Competition (ANAC) is used by the automated negotiation research community to benchmark and evaluate its work andto challenge itself. The benchmark problems and evaluation results and the protocols and strategies developed are available to the wider research community.

Cognitive agents operating in complex and dynamic domains benefit from significant goal management. Operations on goals include formulation, selection, change, monitoring and delegation in addition to goal achievement. Here we model these operations as transformations on goals. An agent may observe events that affect the agent’s ability to achieve its goals. Hence goal transformations allow unachievable goals to be converted into similar achievable goals. This paper examines an implementation of goal change within a cognitive architecture. We introduce goal transformation at the metacognitive level as well as goal transformation in an automated planner and discuss the costs and benefits of each approach. We evaluate goal change in the MIDCA architecture using a resource-restricted planning domain, demonstrating a performance benefit due to goal operations.

To design social choice mechanisms with desirable utility properties, normative properties, and low sample complexity, we propose a new randomized mechanism called 2-Agree. This mechanism asks random voters for their top alternatives until at least two voters agree, at which point it selects that alternative as the winner. We prove that, despite its simplicity and low sample complexity, 2-Agree achieves almost optimal distortion on a metric space when the number of alternatives is not large, and satisfies anonymity, neutrality, ex-post Pareto efficiency, very strong SD-participation, and is approximately truthful. We further show that 2-Agree works well for larger number of alternatives with decisive agents.

We propose a model-based approach to hierarchical reinforcement learning that exploits shared knowledge and selective execution at different levels of abstraction, to efficiently solve large, complex problems. Our framework adopts a new transition dynamics learning algorithm that identifies the common action-feature combinations of the subtasks, and evaluates the subtask execution choices through simulation. The framework is sample efficient, and tolerates uncertain and incomplete problem characterization of the subtasks. We test the framework on common benchmark problems and complex simulated robotic environments. It compares favorably against the state-of-the-art algorithms, and scales well in very large problems.

We present a new game-theoretic framework in which Bayesian players with bounded rationality engage in a Markov game and each has private but incomplete information regarding other players' types. Instead of utilizing Harsanyi's abstract types and a common prior, we construct intentional player types whose structure is explicit and induces a {\em finite-level} belief hierarchy. We characterize an equilibrium in this game and establish the conditions for existence of the equilibrium. The computation of finding such equilibria is formalized as a constraint satisfaction problem and its effectiveness is demonstrated on two cooperative domains.

The Man-In-The-Middle (MITM) attack is one of the most common attacks employed in the network hacking. MITM attackers can successfully invoke attacks such as denial of service (DoS) and port stealing, and lead to surprisingly harmful consequences for users in terms of both financial loss and security issues. The conventional defense approaches mainly consider how to detect and eliminate those attacks or how to prevent those attacks from being launched in the first place. This paper proposes a game-theoretic defense strategy from a different perspective, which aims at minimizing the loss that the whole system sustains given that the MITM attacks are inevitable. We model the interaction between the attacker and the defender as a Stackelberg security game and adopt the Strong Stackelberg Equilibrium (SSE) as the defender's strategy. Since the defender's strategy space is infinite in our model, we employ a novel method to reduce the searching space of computing the optimal defense strategy. Finally, we empirically evaluate our optimal defense strategy by comparing it with non-strategic defense strategies. The results indicate that our game-theoretic defense strategy significantly outperforms other non-strategic defense strategies in terms of decreasing the total losses against MITM attacks.

A repeated game is a formal model for analyzing cooperation in long-term relationships, e.g., in the prisoner's dilemma. Although the case where each player observes her opponent's action with some observation errors (imperfect private monitoring) is difficult to analyze, a special type of an equilibrium called belief-free equilibrium is identified to make the analysis in private monitoring tractable. However, existing works using a belief-free equilibrium show that cooperative relations can be sustainable only in ideal situations. We deal with a generic problem that can model both the prisoner's dilemma and the team production problem. We examine a situation with an additional action that is dominated by another action. To our surprise, by adding this seemingly irrelevant action, players can achieve sustainable cooperative relations far beyond the ideal situations. More specifically, we identify a class of strategies called one-shot punishment strategy that can constitute a belief-free equilibrium in a wide range of parameters. Moreover, for a two-player case, the obtained welfare matches a theoretical upper bound.