Monte Carlo Tree Search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling. It has received considerable interest due to its spectacular success in the difficult problem of computer Go, but has also proved beneficial in a range of other domains. This paper is a survey of the literature to date, intended to provide a snapshot of the state of the art after the first five years of MCTS research. We outline the core algorithm's derivation, impart some structure on the many variations and enhancements that have been proposed, and summarise the results from the key game and non-game domains to which MCTS methods have been applied. A number of open research questions indicate that the field is ripe for future work.

This paper investigates the applicability of Genetic Programming type systems to dynamic game environments. Grammatical Evolution was used to evolve Behaviour Trees, in order to create controllers for the Mario AI Benchmark. The results obtained reinforce the applicability of evolutionary programming systems to the development of artificial intelligence in games, and in dynamic systems in general, illustrating their viability as an alternative to more standard AI techniques.

While most collaboration technologies are concerned with supporting particular tasks such as workflows or meetings, many work groups do not have the teamwork skills essential to effective collaboration. One way to improve teamwork is to provide dynamic feedback generated by automated analyses of behavior, such as language use. Such feedback can lead members to reflect on and subsequently improve their collaborative behavior, but might also distract from the task at hand. We have experimented with GroupMeter -a chatbased system that presents visual feedback on team members' language use. Feedback on proportion of agreement words and overall word count was presented using two different designs. When receiving feedback, teams in our study expressed more agreement in their conversations and reported greater focus on language use as compared to when not receiving feedback. This suggests that automated, realtime linguistic feedback can elicit behavioral changes, offering opportunities for future research.

In real-time games, agents have limited time to respond to environmental cues. This requires either a policy defined up-front or, if one has access to a generative model, a very efficient rolling horizon search. In this paper, different search techniques are compared in a simple, yet interesting, realtime game known as the Physical Travelling Salesman Problem (PTSP). We introduce a rolling horizon version of a simple evolutionary algorithm that handles macro-actions and compare it against Monte Carlo Tree Search (MCTS), an approach known to perform well in practice, as well as random search. The experimental setup employs a variety of settings for both the action space of the agent as well as the algorithms used. We show that MCTS is able to handle very fine-grained searches whereas evolution performs better as we move to coarser-grained actions; the choice of algorithm becomes irrelevant if the actions are even more coarse-grained. We conclude that evolutionary algorithms can be a viable and competitive alternative to MCTS.

Abstract-General Video Game Playing is a game AI domain in which the usage of game-dependent domain knowledge is very limited or even non existent. This imposes obvious difficulties when seeking to create agents able to play sets of different games. Taken more broadly, this issue can be used as an introduction to the field of General Artificial Intelligence. This paper explores the performance of a vanilla Monte Carlo Tree Search algorithm, and analyzes the main difficulties encountered when tackling this kind of scenarios. Modifications are proposed to overcome these issues, strengthening the algorithm's ability to gather and discover knowledge, and taking advantage of past experiences. Results show that the performance of the algorithm is significantly improved, although there remain unresolved problems that require further research. The framework employed in this research is publicly available and will be used in the General Video Game Playing competition at the IEEE Conference on Computational Intelligence and Games in 2014.