Learn More
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,(More)
Upper Confidence Trees are a very efficient tool for solving Markov Decision Processes; originating in difficult games like the game of Go, it is in particular surprisingly efficient in high dimensional problems. It is known that it can be adapted to continuous domains in some cases (in particular continuous action spaces). We here present an extension of(More)
Monte Carlo Tree Search (MCTS) was born in Computer Go, i.e. in the application of artificial intelligence to the game of Go. Since its creation, in 2006, many improvements have been published. Programs are still by far weaker than the best human players, yet the gap was very significantly reduced. MCTS is now widely applied in games, in particular when no(More)
HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt età la diffusion(More)
In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been proposed, but the benchmarks used to compare them are only relevant for specific cases. The paper addresses this(More)
Upper Confidence Trees (UCT) are now a well known algorithm for sequential decision making; it is a provably consistent variant of Monte-Carlo Tree Search. However, the consistency is only proved in a the case where both the action space is finite. We here propose a proof in the case of fully observable Markov Decision Processes with bounded horizon,(More)
In the standard version of the UCT algorithm, in the case of a continuous set of decisions, the exploration of new decisions is done through blind search. This can lead to very inefficient exploration, particularly in the case of large dimension problems, which often happens in energy management problems, for instance. In an attempt to use the information(More)
Current state of the art methods in energy policy planning only approximate the problem (Linear Programming on a finite sample of scenarios, Dynamic Programming on an approximation of the problem , etc). Monte-Carlo Tree Search (MCTS [3]) seems to be a potential candidate to converge to an exact solution of these problems ([2]). But how fast, and how do key(More)
Many decision problems have two levels: one for strategic decisions, and another for tactical management. This paper focuses on the strategic level, more specifically the sequential exploration of the possible options and the final selection (recommendation) of the best option. Several sequential exploration and recommendation criteria are considered and(More)