Min, Wookhee (North Carolina State University) | Baikadi, Alok (University of Pittsburgh) | Mott, Bradford (North Carolina State University) | Rowe, Jonathan (North Carolina State University) | Liu, Barry (North Carolina State University) | Ha, Eun Young (IBM) | Lester, James (North Carolina State University)
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.
Bard, Nolan, Foerster, Jakob N., Chandar, Sarath, Burch, Neil, Lanctot, Marc, Song, H. Francis, Parisotto, Emilio, Dumoulin, Vincent, Moitra, Subhodeep, Hughes, Edward, Dunning, Iain, Mourad, Shibl, Larochelle, Hugo, Bellemare, Marc G., Bowling, Michael
From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making. In recent years, machine learning has made dramatic advances with artificial agents reaching superhuman performance in challenge domains like Go, Atari, and some variants of poker. As with their predecessors of chess, checkers, and backgammon, these game domains have driven research by providing sophisticated yet well-defined challenges for artificial intelligence practitioners. We continue this tradition by proposing the game of Hanabi as a new challenge domain with novel problems that arise from its combination of purely cooperative gameplay and imperfect information in a two to five player setting. In particular, we argue that Hanabi elevates reasoning about the beliefs and intentions of other agents to the foreground. We believe developing novel techniques capable of imbuing artificial agents with such theory of mind will not only be crucial for their success in Hanabi, but also in broader collaborative efforts, and especially those with human partners. To facilitate future research, we introduce the open-source Hanabi Learning Environment, propose an experimental framework for the research community to evaluate algorithmic advances, and assess the performance of current state-of-the-art techniques.
In conjunction with the Association for the Advancement of Artificial Intelligence's Hall of Champions exhibit, the Innovative Applications of Artificial Intelligence held a panel discussion entitled "AI Game-Playing Techniques: Are They Useful for Anything Other Than Games?" This article summarizes the panelists' comments about whether ideas and techniques from AI game playing are useful elsewhere and what kinds of game might be suitable as "challenge problems" for future research.
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.
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.