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.

As far back as the industrial revolution, significant development in technical innovation has succeeded in transforming numerous manual tasks and processes that had been in existence for decades where humans had reached the limits of physical capacity. Artificial Intelligence (AI) offers this same transformative potential for the augmentation and potential replacement of human tasks and activities within a wide range of industrial, intellectual and social applications. The pace of change for this new AI technological age is staggering, with new breakthroughs in algorithmic machine learning and autonomous decision-making, engendering new opportunities for continued innovation. The impact of AI could be significant, with industries ranging from: finance, healthcare, manufacturing, retail, supply chain, logistics and utilities, all potentially disrupted by the onset of AI technologies. The study brings together the collective insight from a number of leading expert contributors to highlight the significant opportunities, realistic assessment of impact, challenges and potential research agenda posed by the rapid emergence of AI within a number of domains: business and management, government, public sector, and science and technology. This research offers significant and timely insight to AI technology and its impact on the future of industry and society in general, whilst recognising the societal and industrial influence on pace and direction of AI development.

This paper describes a variational free-energy formulation of (partially observable) Markov decision problems in decision making under uncertainty. We show that optimal control can be cast as active inference. In active inference, both action and posterior beliefs about hidden states minimise a free energy bound on the negative log-likelihood of observed states, under a generative model. In this setting, reward or cost functions are absorbed into prior beliefs about state transitions and terminal states. Effectively, this converts optimal control into a pure inference problem, enabling the application of standard Bayesian filtering techniques. We then consider optimal trajectories that rest on posterior beliefs about hidden states in the future. Crucially, this entails modelling control as a hidden state that endows the generative model with a representation of agency. This leads to a distinction between models with and without inference on hidden control states; namely, agency-free and agency-based models, respectively.

Abstract-This paper presents the framework, rules, games, controllers and results of the first General Video Game Playing Competition, held at the IEEE Conference on Computational Intelligence and Games in 2014. The competition proposes the challenge of creating controllers for general video game play, where a single agent must be able to play many different games, some of them unknown to the participants at the time of submitting their entries. This test can be seen as an approximation of General Artificial Intelligence, as the amount of game-dependent heuristics needs to be severely limited.The games employed are stochastic real-time scenarios (where the time budget to provide the next action is measured in milliseconds) with different winning conditions, scoring mechanisms, sprite types and available actions for the player. It is a responsibility of the agents to discover the mechanics of each game, the requirements to obtain a high score and the requisites to finally achieve victory. This paper describes all controllers submitted to the competition, with an in-depth description of four of them by their authors, including the winner and the runner-up entries of the contest. The paper also analyzes the performance of the different approaches submitted, and finally proposes future tracks for the competition.

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.