Search Results for author:
Found 29 papers, 8 papers with code
Predictive Control Using Learned State Space Models via Rolling Horizon Evolution
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.
Modulation of viability signals for self-regulatory control
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.
Evaluating Generalisation in General Video Game Playing
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.
Bootstrapped model learning and error correction for planning with uncertainty in model-based RL
Having access to a forward model enables the use of planning algorithms such as Monte Carlo Tree Search and Rolling Horizon Evolution.
Enhanced Rolling Horizon Evolution Algorithm with Opponent Model Learning: Results for the Fighting Game AI Competition
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.
Rolling Horizon Evolutionary Algorithms for General Video Game Playing
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.
Learning Local Forward Models on Unforgiving Games
This paper examines learning approaches for forward models based on local cell transition functions.
Project Thyia: A Forever Gameplayer
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.
Foundations of Digital Archæoludology
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.
Tile Pattern KL-Divergence for Analysing and Evolving Game Levels
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.
A Local Approach to Forward Model Learning: Results on the Game of Life Game
This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent.
Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best
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.
Game AI Research with Fast Planet Wars Variants
This paper describes a new implementation of Planet Wars, designed from the outset for Game AI research.
Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network
This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus.
General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms
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).
The N-Tuple Bandit Evolutionary Algorithm for Game Agent Optimisation
This paper describes the N-Tuple Bandit Evolutionary Algorithm (NTBEA), an optimisation algorithm developed for noisy and expensive discrete (combinatorial) optimisation problems.
Efficient Noisy Optimisation with the Sliding Window Compact Genetic Algorithm
The compact genetic algorithm is an Estimation of Distribution Algorithm for binary optimisation problems.
Evaluating Noisy Optimisation Algorithms: First Hitting Time is Problematic
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.
Evaluating and Modelling Hanabi-Playing Agents
Agent modelling involves considering how other agents will behave, in order to influence your own actions.
Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing
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.
General Video Game AI: Learning from Screen Capture
General Video Game Artificial Intelligence is a general game playing framework for Artificial General Intelligence research in the video-games domain.
Population Seeding Techniques for Rolling Horizon Evolution in General Video Game Playing
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.
The N-Tuple Bandit Evolutionary Algorithm for Automatic Game Improvement
This paper describes a new evolutionary algorithm that is especially well suited to AI-Assisted Game Design.
Evolving Game Skill-Depth using General Video Game AI Agents
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.
Ms. Pac-Man Versus Ghost Team CIG 2016 Competition
This paper introduces the revival of the popular Ms. Pac-Man Versus Ghost Team competition.
Optimal resampling for the noisy OneMax problem
The OneMax problem is a standard benchmark optimisation problem for a binary search space.
Rolling Horizon Coevolutionary Planning for Two-Player Video Games
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.
Bandit-Based Random Mutation Hill-Climbing
The Random Mutation Hill-Climbing algorithm is a direct search technique mostly used in discrete domains.
A Survey of Monte Carlo Tree Search Methods
Monte Carlo Tree Search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling.
