Socially Intelligent Agents to Improve the Effectiveness of Educational Games

AAAI Conferences

We describe preliminary research on devising intelligent agents that can improve the educational effectiveness of collaborative, educational computer games. We illustrate how these agents can overcome some of the shortcomings of educational games by explicitly monitoring how students interact with the games, by modeling both the students' cognitive and emotional states, and by generating calibrated interventions to trigger constructive reasoning and reflection when needed. Introduction In this paper, we explore the potential of enriching educational computer games with socially intelligent agents that can help students learn effectively from the games while maintaining the high level of engagement and motivation that constitutes the strong appeal of electronic games in non-educational settings. Our research is developed in the context of EGEMS, the Electronic Games for Education in Math and Science project at the University of British Columbia (UBC). EGEMS is an interdisciplinary project that aims to explore the potential of specially designed computer and video games in mathematics and science education for students aged 9 - 13. Several authors have suggested the potential of video and computer games as educational tools (e.g.


Macro-FF: Improving AI Planning with Automatically Learned Macro-Operators

AAAI Conferences

Despite recent progress in AI planning, many benchmarks remain challenging for current planners. In many domains, the performance of a planner can greatly be improved by discovering and exploiting information about the domain structure that is not explicitly encoded in the initial PDDL formulation. In this paper we present and compare two automated methods that learn relevant information from previous experience in a domain and use it to solve new problem instances. Our methods share a common four-step strategy. First, a domain is analyzed and structural information is extracted, then macro-operators are generated based on the previously discovered structure.


Macro-FF: Improving AI Planning with Automatically Learned Macro-Operators

arXiv.org Artificial Intelligence

Despite recent progress in AI planning, many benchmarks remain challenging for current planners. In many domains, the performance of a planner can greatly be improved by discovering and exploiting information about the domain structure that is not explicitly encoded in the initial PDDL formulation. In this paper we present and compare two automated methods that learn relevant information from previous experience in a domain and use it to solve new problem instances. Our methods share a common four-step strategy. First, a domain is analyzed and structural information is extracted, then macro-operators are generated based on the previously discovered structure. A filtering and ranking procedure selects the most useful macro-operators. Finally, the selected macros are used to speed up future searches. We have successfully used such an approach in the fourth international planning competition IPC-4. Our system, Macro-FF, extends Hoffmanns state-of-the-art planner FF 2.3 with support for two kinds of macro-operators, and with engineering enhancements. We demonstrate the effectiveness of our ideas on benchmarks from international planning competitions. Our results indicate a large reduction in search effort in those complex domains where structural information can be inferred.


Macro-FF: Improving AI Planning with Automatically Learned Macro-Operators

Journal of Artificial Intelligence Research

Despite recent progress in AI planning, many benchmarks remain challenging for current planners. In many domains, the performance of a planner can greatly be improved by discovering and exploiting information about the domain structure that is not explicitly encoded in the initial PDDL formulation. In this paper we present and compare two automated methods that learn relevant information from previous experience in a domain and use it to solve new problem instances. Our methods share a common four-step strategy. First, a domain is analyzed and structural information is extracted, then macro-operators are generated based on the previously discovered structure. A filtering and ranking procedure selects the most useful macro-operators. Finally, the selected macros are used to speed up future searches. We have successfully used such an approach in the fourth international planning competition IPC-4. Our system, Macro-FF, extends Hoffmann's state-of-the-art planner FF 2.3 with support for two kinds of macro-operators, and with engineering enhancements. We demonstrate the effectiveness of our ideas on benchmarks from international planning competitions. Our results indicate a large reduction in search effort in those complex domains where structural information can be inferred.


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

#artificialintelligence

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.