A Generalized Multidimensional Evaluation Framework for Player Goal Recognition

AAAI Conferences

Recent years have seen a growing interest in player modeling, which supports the creation of player-adaptive digital games. A central problem of player modeling is goal recognition, which aims to recognize players’ intentions from observable gameplay behaviors. Player goal recognition offers the promise of enabling games to dynamically adjust challenge levels, perform procedural content generation, and create believable NPC interactions. A growing body of work is investigating a wide range of machine learning-based goal recognition models. In this paper, we introduce GOALIE, a multidimensional framework for evaluating player goal recognition models. The framework integrates multiple metrics for player goal recognition models, including two novel metrics, n-early convergence rate and standardized convergence point . We demonstrate the application of the GOALIE framework with the evaluation of several player goal recognition models, including Markov logic network-based, deep feedforward neural network-based, and long short-term memory network-based goal recognizers on two different educational games. The results suggest that GOALIE effectively captures goal recognition behaviors that are key to next-generation player modeling.

Divide and conquer: How Microsoft researchers used AI to master Ms. Pac-Man - Next at Microsoft


Microsoft researchers have created an artificial intelligence-based system that learned how to get the maximum score on the addictive 1980s video game Ms. Pac-Man, using a divide-and-conquer method that could have broad implications for teaching AI agents to do complex tasks that augment human capabilities. The team from Maluuba, a Canadian deep learning startup acquired by Microsoft earlier this year, used a branch of AI called reinforcement learning to play the Atari 2600 version of Ms. Pac-Man perfectly. Using that method, the team achieved the maximum score possible of 999,990. Doina Precup, an associate professor of computer science at McGill University in Montreal said that's a significant achievement among AI researchers, who have been using various videogames to test their systems but have found Ms. Pac-Man among the most difficult to crack. But Precup said she was impressed not just with what the researchers achieved but with how they achieved it.


AAAI Conferences

Much of the work on opponent modeling for game tree search has been unsuccessful. In two-player, zero-sum games, the gains from opponent modeling are often outweighed by the cost of modeling.

Department of Information and Communication Engineering University of Tokyo, Japan hy@logos.ic.i.u-tokyo.ac.jp

AAAI Conferences

Monte Carlo Go is a promising method to improve the performance of computer Go programs. This approach determines the next move to play based on many Monte Carlo samples. This paper examines the relative advantages of additional samples and enhancements for Monte Carlo Go. By parallelizing Monte Carlo Go, we could increase sample sizes by two orders of magnitude. Experimental results obtained in 9 9 Go show strong evidence that there are tradeoffs among these advantages and performance, indicating a way for Monte Carlo Go to go.

Using Cyclic Scheduling to Generate Believable Behavior in Games

AAAI Conferences

Video game virtual characters should interact with the player, each other, and the environment. However, the cost of scripting complex behaviors becomes a bottleneck in content creation. Our goal is to help game designers to more easily populate their open world with background characters that exhibit more believable behaviors. We use a cyclic scheduling model that generates dynamic schedules for the daily lives of virtual characters. The scheduler employs a tiered behavior architecture where behavior components are modular and reusable. This research validates the designer usability of an implementation of this model. We present the results of a user study that evaluates the scheduling system versus manual scripting based on three metrics of behavior creation: behavior completeness, behavior correctness and behavior implementation time. The results indicate that the behavior architecture produces more reliable behaviors and improves designer efficiency which will reduce the cost of generating more believable character behaviors.