no code implementations • 25 Jun 2021 • Alvaro Ovalle, Simon M. Lucas
A large part of the interest in model-based reinforcement learning derives from the potential utility to acquire a forward model capable of strategic long term decision making.
no code implementations • 18 Jul 2020 • Alvaro Ovalle, Simon M. Lucas
In particular, we highlight the distinction between observations induced by the environment and those pertaining more directly to the continuity of an agent in time.
no code implementations • 22 May 2020 • Martin Balla, Simon M. Lucas, Diego Perez-Liebana
This paper focuses on the challenge of the GVGAI learning track in which 3 games are selected and 2 levels are given for training, while 3 hidden levels are left for evaluation.
no code implementations • 15 Apr 2020 • Alvaro Ovalle, Simon M. Lucas
Having access to a forward model enables the use of planning algorithms such as Monte Carlo Tree Search and Rolling Horizon Evolution.
no code implementations • 31 Mar 2020 • Zhentao Tang, Yuanheng Zhu, Dongbin Zhao, Simon M. Lucas
In contrast to conventional RHEA, an opponent model is proposed and is optimized by supervised learning with cross-entropy and reinforcement learning with policy gradient and Q-learning respectively, based on history observations from opponent.
1 code implementation • 27 Mar 2020 • Raluca D. Gaina, Sam Devlin, Simon M. Lucas, Diego Perez-Liebana
Game-playing Evolutionary Algorithms, specifically Rolling Horizon Evolutionary Algorithms, have recently managed to beat the state of the art in win rate across many video games.
1 code implementation • 1 Sep 2019 • Alexander Dockhorn, Simon M. Lucas, Vanessa Volz, Ivan Bravi, Raluca D. Gaina, Diego Perez-Liebana
This paper examines learning approaches for forward models based on local cell transition functions.
no code implementations • 10 Jun 2019 • Raluca D. Gaina, Simon M. Lucas, Diego Perez-Liebana
Similarly, AI game-players are run once on a game (or maybe for longer periods of time, in the case of learning algorithms which need some, still limited, period for training), and they cease to exist once the game ends.
no code implementations • 31 May 2019 • Cameron Browne, Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Michael Conrad, Walter Crist, Thierry Depaulis, Eddie Duggan, Fred Horn, Steven Kelk, Simon M. Lucas, João Pedro Neto, David Parlett, Abdallah Saffidine, Ulrich Schädler, Jorge Nuno Silva, Alex de Voogt, Mark H. M. Winands
Digital Archaeoludology (DAL) is a new field of study involving the analysis and reconstruction of ancient games from incomplete descriptions and archaeological evidence using modern computational techniques.
no code implementations • 24 Apr 2019 • Simon M. Lucas, Vanessa Volz
This paper provides a detailed investigation of using the Kullback-Leibler (KL) Divergence as a way to compare and analyse game-levels, and hence to use the measure as the objective function of an evolutionary algorithm to evolve new levels.
no code implementations • 29 Mar 2019 • Simon M. Lucas, Alexander Dockhorn, Vanessa Volz, Chris Bamford, Raluca D. Gaina, Ivan Bravi, Diego Perez-Liebana, Sanaz Mostaghim, Rudolf Kruse
This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent.
1 code implementation • 3 Jan 2019 • Simon M. Lucas, Jialin Liu, Ivan Bravi, Raluca D. Gaina, John Woodward, Vanessa Volz, Diego Perez-Liebana
This paper introduces a simple and fast variant of Planet Wars as a test-bed for statistical planning based Game AI agents, and for noisy hyper-parameter optimisation.
no code implementations • 22 Jun 2018 • Simon M. Lucas
This paper describes a new implementation of Planet Wars, designed from the outset for Game AI research.
3 code implementations • 2 May 2018 • Vanessa Volz, Jacob Schrum, Jialin Liu, Simon M. Lucas, Adam Smith, Sebastian Risi
This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus.
1 code implementation • 28 Feb 2018 • Diego Perez-Liebana, Jialin Liu, Ahmed Khalifa, Raluca D. Gaina, Julian Togelius, Simon M. Lucas
In 2014, The General Video Game AI (GVGAI) competition framework was created and released with the purpose of providing researchers a common open-source and easy to use platform for testing their AI methods with potentially infinity of games created using Video Game Description Language (VGDL).
4 code implementations • 16 Feb 2018 • Simon M. Lucas, Jialin Liu, Diego Perez-Liebana
This paper describes the N-Tuple Bandit Evolutionary Algorithm (NTBEA), an optimisation algorithm developed for noisy and expensive discrete (combinatorial) optimisation problems.
no code implementations • 7 Aug 2017 • Simon M. Lucas, Jialin Liu, Diego Pérez-Liébana
The compact genetic algorithm is an Estimation of Distribution Algorithm for binary optimisation problems.
no code implementations • 13 Jun 2017 • Simon M. Lucas, Jialin Liu, Diego Pérez-Liébana
A frequently used stopping condition in runtime analysis, known as "First Hitting Time", is to stop the algorithm as soon as it encounters the optimal solution.
no code implementations • 24 Apr 2017 • Joseph Walton-Rivers, Piers R. Williams, Richard Bartle, Diego Perez-Liebana, Simon M. Lucas
Agent modelling involves considering how other agents will behave, in order to influence your own actions.
no code implementations • 24 Apr 2017 • Raluca D. Gaina, Jialin Liu, Simon M. Lucas, Diego Perez-Liebana
Monte Carlo Tree Search techniques have generally dominated General Video Game Playing, but recent research has started looking at Evolutionary Algorithms and their potential at matching Tree Search level of play or even outperforming these methods.
no code implementations • 23 Apr 2017 • Kamolwan Kunanusont, Simon M. Lucas, Diego Perez-Liebana
General Video Game Artificial Intelligence is a general game playing framework for Artificial General Intelligence research in the video-games domain.
no code implementations • 23 Apr 2017 • Rauca D. Gaina, Simon M. Lucas, Diego Perez-Liebana
While Monte Carlo Tree Search and closely related methods have dominated General Video Game Playing, recent research has demonstrated the promise of Rolling Horizon Evolutionary Algorithms as an interesting alternative.
2 code implementations • 18 Mar 2017 • Kamolwan Kunanusont, Raluca D. Gaina, Jialin Liu, Diego Perez-Liebana, Simon M. Lucas
This paper describes a new evolutionary algorithm that is especially well suited to AI-Assisted Game Design.
no code implementations • 18 Mar 2017 • Jialin Liu, Julian Togelius, Diego Perez-Liebana, Simon M. Lucas
The space of possible parameter settings can be seen as a search space, and we can therefore use a Random Mutation Hill Climbing algorithm or other search methods to find the parameter settings that induce the best games.
no code implementations • 8 Sep 2016 • Piers R. Williams, Diego Perez-Liebana, Simon M. Lucas
This paper introduces the revival of the popular Ms. Pac-Man Versus Ghost Team competition.
no code implementations • 22 Jul 2016 • Jialin Liu, Michael Fairbank, Diego Pérez-Liébana, Simon M. Lucas
The OneMax problem is a standard benchmark optimisation problem for a binary search space.
no code implementations • 6 Jul 2016 • Jialin Liu, Diego Pérez-Liébana, Simon M. Lucas
To select an action the algorithm co-evolves two (or in the general case N) populations, one for each player, where each individual is a sequence of actions for the respective player.
no code implementations • 20 Jun 2016 • Jialin Liu, Diego Peŕez-Liebana, Simon M. Lucas
The Random Mutation Hill-Climbing algorithm is a direct search technique mostly used in discrete domains.
1 code implementation • IEEE Transactions on Computational Intelligence and AI in Games 2012 • Cameron B. Browne, Edward Powley, Daniel Whitehouse, Simon M. Lucas, Peter I. Cowling, Philipp Rohlfshagen, Stephen Tavener, Diego Perez, Spyridon Samothrakis, Simon Colton
Monte Carlo Tree Search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling.