The process of play testing a game is subjective, expensive and incomplete. In this paper, we present a play-testing approach that explores the game space with automated agents and collects data to answer questions posed by the designers. Rather than have agents interacting with an actual game client, this approach recreates the bare bone mechanics of the game as a separate system. Our agent is able to play in minutes what would take testers days of organic gameplay. The analysis of thousands of game simulations exposed imbalances in game actions, identified inconsequential rewards and evaluated the effectiveness of optional strategic choices. Our test case game, The Sims Mobile, was recently released and the findings shown here influenced design changes that resulted in improved player experience.

Intelligent interactive narrative systems often use an experience manager to govern the behavior of non-player charactersin a way that guides the story towards its author’s agenda, which may be for entertainment, education, training, or other purposes. For such systems, a central challenge is creating believable virtual characters. The Belief Desire Intention framework is often cited as a goal for researchers in this field; for characters to seem realistic, a human audience should attribute beliefs, desires, and intentions to them. Much of my prior work has focused on belief; my goal for the future is to finish the work on belief, and to implement a new model of desire and intention that explicitly reasons about characters’ commitment to certain plans of action.

Rational agents are becoming prevalent in many domains, from data analysis to entertainment and games. The increased prevalence of agents has evolved new tools and techniques to work with and design new agents. One such technique is system simulation. Systems simulation is a technique an author can use to imitate tasks, processes, or systems, and in particular, agents. Systems simulation has a variety of uses, ranging from simulating ecological systems to entertainment, such as interactive narratives and digital games. However, many system simulators use specialized programming languages and require prior programming experience. This causes a disconnect between individuals with limited programming experience who wish to use the simulation tools, and the software itself. New users may find the specialized languages daunting, and the initial learning process too intense for the anticipated reward. This research strives to bridge the gap between system simulation tools and users with little to no programming experience. Future work includes a corpus of narrative and autonomous agent creation tools designed for users with little to no programming experience.

Many modern creative industrial processes rely on the collaboration between multiple humans, assisted by one or more computational systems, in a complex environment. However, most traditional systems lack the adaptability required to contribute in a flexible, co-creative manner, instead executing a fixed set of tasks in a preset time schedule. We believe games, especially cooperative games offer an ideal platform to conduct research in co-creativity. We present our motivation, preliminary work and future goals to study, build and measure game-inspired co-creative AI systems.

Intelligent autonomous agents that are acting in dynamic environmentsin real-time are often required to follow long-termstrategies while also remaining reactive and being able to actdeliberately. In order to create intelligent behaviors for videogame characters, there are two common approaches – plannersare used for long-term strategical planning, whereas BehaviorTrees allow for reactive acting. Although both methodologieshave their advantages, when used on their own, theyfail to fully achieve both requirements described above. Inthis work, we propose a hybrid approach combining a HierarchicalTask Network planner for high-level planning whiledelegating low-level decision making and acting to BehaviorTrees. Furthermore, we compare this approach with a pureplanner in a multi-agent environment.

Social deduction games present a unique challenge for AI agents, because communication plays a central role in most of them, and deception plays a key role in game play. To be successful in such games, players need to come up with convincing stories, but also discern the truth of statements of other players and adapt to the information learned from them. In this paper we present an approach for virtual agents that have to determine how long to stick to their story in the light of information obtained from other players. We apply this approach to a particular social deduction game, One Night Ultimate Werewolf, and demonstrate the effect of different levels of commitment to an agent's story.

As one of Bayesian analysis tools, Hidden Markov Model (HMM) has been used to in extensive applications. Most HMMs are solved by Baum-Welch algorithm (BWHMM) to predict the model parameters, which is difficult to find global optimal solutions. This paper proposes an optimized Hidden Markov Model with Particle Swarm Optimization (PSO) algorithm and so is called PSOHMM. In order to overcome the statistical constraints in HMM, the paper develops re-normalization and re-mapping mechanisms to ensure the constraints in HMM. The experiments have shown that PSOHMM can search better solution than BWHMM, and has faster convergence speed.

Bribery in election (or computational social choice in general) is an important problem that has received a considerable amount of attention. In the classic bribery problem, the briber (or attacker) bribes some voters in attempting to make the briber's designated candidate win an election. In this paper, we introduce a novel variant of the bribery problem, "Election with Bribed Voter Uncertainty" or BVU for short, accommodating the uncertainty that the vote of a bribed voter may or may not be counted. This uncertainty occurs either because a bribed voter may not cast its vote in fear of being caught, or because a bribed voter is indeed caught and therefore its vote is discarded. As a first step towards ultimately understanding and addressing this important problem, we show that it does not admit any multiplicative $O(1)$-approximation algorithm modulo standard complexity assumptions. We further show that there is an approximation algorithm that returns a solution with an additive-$\epsilon$ error in FPT time for any fixed $\epsilon$.

-- a group of intelligent agents which fulfill a set of tasks in parallel is represented first by the tensor multiplication of corresponding processes in a linear logic game category. An optimal itinerary in the configuration space of the group states is defined as a play with maximal total reward in the category. New moments also are: the reward is represented as a degree of certainty (visibility) of an agent goal, and the system goals are chosen by the greatest value corresponding to these processes in the system goal lattice. The artificial intelligence is represented in the Artificial General Intelligence (AGI) approach as an information processor which consumes and gives out information. Investigations in the field are focused on systems which act rationally. A formal description of the most intelligent agent (AIXI) behavior, in the sense of some intelligence measure, is suggested in AGI framework [1].

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function representing discounted return. In this paper, we examine the role of these policy gradient and actor-critic algorithms in partially-observable multiagent environments. We show several candidate policy update rules and relate them to a foundation of regret minimization and multiagent learning techniques for the one-shot and tabular cases, leading to previously unknown convergence guarantees. We apply our method to model-free multiagent reinforcement learning in adversarial sequential decision problems (zero-sum imperfect information games), using RL-style function approximation. We evaluate on commonly used benchmark Poker domains, showing performance against fixed policies and empirical convergence to approximate Nash equilibria in self-play with rates similar to or better than a baseline model-free algorithm for zero-sum games, without any domain-specific state space reductions.