Simon M. Lucas

Xiulei Song, Yizhao Jin, Greg Slabaugh et al.

PPO (Proximal Policy Optimization) is a state-of-the-art policy gradient algorithm that has been successfully applied to complex computer games such as Dota 2 and Honor of Kings. In these environments, an agent makes compound actions consisting of multiple sub-actions. PPO uses clipping to restrict policy updates. Although clipping is simple and effective, it is not efficient in its sample use. For compound actions, most PPO implementations consider the joint probability (density) of sub-actions, which means that if the ratio of a sample (state compound-action pair) exceeds the range, the gradient the sample produces is zero. Instead, for each sub-action we calculate the loss separately, which is less prone to clipping during updates thereby making better use of samples. Further, we propose a multi-action mixed loss that combines joint and separate probabilities. We perform experiments in Gym-$μ$RTS and MuJoCo. Our hybrid model improves performance by more than 50\% in different MuJoCo environments compared to OpenAI's PPO benchmark results. And in Gym-$μ$RTS, we find the sub-action loss outperforms the standard PPO approach, especially when the clip range is large. Our findings suggest this method can better balance the use-efficiency and quality of samples.

Chris Bamford, Simon Lucas

Access to a fast and easily copied forward model of a game is essential for model-based reinforcement learning and for algorithms such as Monte Carlo tree search, and is also beneficial as a source of unlimited experience data for model-free algorithms. Learning forward models is an interesting and important challenge in order to address problems where a model is not available. Building upon previous work on the Neural GPU, this paper introduces the Neural Game Engine, as a way to learn models directly from pixels. The learned models are able to generalise to different size game levels to the ones they were trained on without loss of accuracy. Results on 10 deterministic General Video Game AI games demonstrate competitive performance, with many of the games models being learned perfectly both in terms of pixel predictions and reward predictions. The pre-trained models are available through the OpenAI Gym interface and are available publicly for future research here: \url{https://github.com/Bam4d/Neural-Game-Engine}

Diego Perez-Liebana, Jialin Liu, Ahmed Khalifa et al.

General Video Game Playing (GVGP) aims at designing an agent that is capable of playing multiple video games with no human intervention. 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 framework has been expanded into several tracks during the last few years to meet the demand of different research directions. The agents are required either to play multiple unknown games with or without access to game simulations, or to design new game levels or rules. This survey paper presents the VGDL, the GVGAI framework, existing tracks, and reviews the wide use of GVGAI framework in research, education and competitions five years after its birth. A future plan of framework improvements is also described.

Xiulei Song, Yizhao Jin, Greg Slabaugh et al.

Estimation of value in policy gradient methods is a fundamental problem. Generalized Advantage Estimation (GAE) is an exponentially-weighted estimator of an advantage function similar to $λ$-return. It substantially reduces the variance of policy gradient estimates at the expense of bias. In practical applications, a truncated GAE is used due to the incompleteness of the trajectory, which results in a large bias during estimation. To address this challenge, instead of using the entire truncated GAE, we propose to take a part of it when calculating updates, which significantly reduces the bias resulting from the incomplete trajectory. We perform experiments in MuJoCo and $μ$RTS to investigate the effect of different partial coefficient and sampling lengths. We show that our partial GAE approach yields better empirical results in both environments.

Yizhao Jin, Greg Slabaugh, Simon Lucas

Deep Reinforcement Learning (DRL) agents frequently face challenges in adapting to tasks outside their training distribution, including issues with over-fitting, catastrophic forgetting and sample inefficiency. Although the application of adapters has proven effective in supervised learning contexts such as natural language processing and computer vision, their potential within the DRL domain remains largely unexplored. This paper delves into the integration of adapters in reinforcement learning, presenting an innovative adaptation strategy that demonstrates enhanced training efficiency and improvement of the base-agent, experimentally in the nanoRTS environment, a real-time strategy (RTS) game simulation. Our proposed universal approach is not only compatible with pre-trained neural networks but also with rule-based agents, offering a means to integrate human expertise.

Fandi Meng, Simon Lucas

We present a game framework tailored for deduction games, enabling structured analysis from the perspective of Shannon entropy variations. Additionally, we introduce a new forward search algorithm, Information Set Entropy Search (ISES), which effectively solves many single-player deduction games. The ISES algorithm, augmented with sampling techniques, allows agents to make decisions within controlled computational resources and time constraints. Experimental results on eight games within our framework demonstrate the significant superiority of our method over the Single Observer Information Set Monte Carlo Tree Search(SO-ISMCTS) algorithm under limited decision time constraints. The entropy variation of game states in our framework enables explainable decision-making, which can also be used to analyze the appeal of deduction games and provide insights for game designers.

James Goodman, Diego Perez-Liebana, Simon Lucas

Games often incorporate random elements in the form of dice or shuffled card decks. This randomness is a key contributor to the player experience and the variety of game situations encountered. There is a tension between a level of randomness that makes the game interesting and contributes to the player enjoyment of a game, and a level at which the outcome itself is effectively random and the game becomes dull. The optimal level for a game will depend on the design goals and target audience. We introduce a new technique to quantify the level of randomness in game outcome and use it to compare 15 tabletop games and disentangle the different contributions to the overall randomness from specific parts of some games. We further explore the interaction between game randomness and player skill, and how this innate randomness can affect error analysis in common game experiments.

Dien Nguyen, Diego Perez-Liebana, Simon Lucas

We introduce JSON Bag-of-Tokens model (JSON-Bag) as a method to generically represent game trajectories by tokenizing their JSON descriptions and apply Jensen-Shannon distance (JSD) as distance metric for them. Using a prototype-based nearest-neighbor search (P-NNS), we evaluate the validity of JSON-Bag with JSD on six tabletop games -- \textit{7 Wonders}, \textit{Dominion}, \textit{Sea Salt and Paper}, \textit{Can't Stop}, \textit{Connect4}, \textit{Dots and boxes} -- each over three game trajectory classification tasks: classifying the playing agents, game parameters, or game seeds that were used to generate the trajectories. Our approach outperforms a baseline using hand-crafted features in the majority of tasks. Evaluating on N-shot classification suggests using JSON-Bag prototype to represent game trajectory classes is also sample efficient. Additionally, we demonstrate JSON-Bag ability for automatic feature extraction by treating tokens as individual features to be used in Random Forest to solve the tasks above, which significantly improves accuracy on underperforming tasks. Finally, we show that, across all six games, the JSD between JSON-Bag prototypes of agent classes highly correlates with the distances between agents' policies.

Manuel Eberhardinger, James Goodman, Alexander Dockhorn et al.

Large language models (LLMs) have shown impressive capabilities in generating program code, opening exciting opportunities for applying program synthesis to games. In this work, we explore the potential of LLMs to directly synthesize usable code for a wide range of gaming applications, focusing on two programming languages, Python and Java. We use an evolutionary hill-climbing algorithm, where the mutations and seeds of the initial programs are controlled by LLMs. For Python, the framework covers various game-related tasks, including five miniature versions of Atari games, ten levels of Baba is You, an environment inspired by Asteroids, and a maze generation task. For Java, the framework contains 12 games from the TAG tabletop games framework. Across 29 tasks, we evaluated 12 language models for Python and 8 for Java. Our findings suggest that the performance of LLMs depends more on the task than on model size. While larger models generate more executable programs, these do not always result in higher-quality solutions but are much more expensive. No model has a clear advantage, although on any specific task, one model may be better. Trying many models on a problem and using the best results across them is more reliable than using just one.

James Goodman, Diego Perez-Liebana, Simon Lucas

We compare four different `game-spaces' in terms of their usefulness in characterising multi-player tabletop games, with a particular interest in any underlying change to a game's characteristics as the number of players changes. In each case we take a 16-dimensional feature space, and reduce it to a 2-dimensional visualizable landscape. We find that a space obtained from optimization of parameters in Monte Carlo Tree Search (MCTS) is the most directly interpretable to characterise our set of games in terms of the relative importance of imperfect information, adversarial opponents and reward sparsity. These results do not correlate with a space defined using attributes of the game-tree. This dimensionality reduction does not show any general effect as the number of players. We therefore consider the question using the original features to classify the games into two sets; those for which the characteristics of the game changes significantly as the number of players changes, and those for which there is no such effect.

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. Assuming that an agent succeeds in learning a useful predictive model, it still requires a mechanism to harness it to generate and select among competing simulated plans. In this paper, we explore this theme combining evolutionary algorithmic planning techniques with models learned via deep learning and variational inference. We demonstrate the approach with an agent that reliably performs online planning in a set of visual navigation tasks.

Ivan Bravi, Simon Lucas

The use of Artificial Intelligence (AI) for play-testing is still on the sidelines of main applications of AI in games compared to performance-oriented game-playing. One of the main purposes of play-testing a game is gathering data on the gameplay, highlighting good and bad features of the design of the game, providing useful insight to the game designers for improving the design. Using AI agents has the potential of speeding the process dramatically. The purpose of this research is to map the behavioural space (BSpace) of a game by using a general method. Using the MAP-Elites algorithm we search the hyperparameter space Rinascimento AI agents and map it to the BSpace defined by several behavioural metrics. This methodology was able to highlight both exemplary and degenerated behaviours in the original game design of Splendor and two variations. In particular, the use of event-value functions has generally shown a remarkable improvement in the coverage of the BSpace compared to agents based on classic score-based reward signals.

James Goodman, Sebastian Risi, Simon Lucas

Recent progress in Game AI has demonstrated that given enough data from human gameplay, or experience gained via simulations, machines can rival or surpass the most skilled human players in classic games such as Go, or commercial computer games such as Starcraft. We review the current state-of-the-art through the lens of wargaming, and ask firstly what features of wargames distinguish them from the usual AI testbeds, and secondly which recent AI advances are best suited to address these wargame-specific features.

Simon M. Lucas

This demo paper describes a simple and practical approach to writing cross-platform casual games using the Kotlin programming language. A key aim is to make it much easier for researchers to demonstrate their AI playing a range of games. Pure Kotlin code (which excludes using any Java graphics libraries) can be transpiled to JavaScript and run in a web browser. However, writing Kotlin code that will run without modification both in a web browser and on the JVM is not trivial; it requires strict adherence to an appropriate methodology. The contribution of this paper is to provide such a method including a software design and to demonstrate this working for Tetris, played either by AI or human.

Alvaro Ovalle, Simon M. Lucas

We revisit the role of instrumental value as a driver of adaptive behavior. In active inference, instrumental or extrinsic value is quantified by the information-theoretic surprisal of a set of observations measuring the extent to which those observations conform to prior beliefs or preferences. That is, an agent is expected to seek the type of evidence that is consistent with its own model of the world. For reinforcement learning tasks, the distribution of preferences replaces the notion of reward. We explore a scenario in which the agent learns this distribution in a self-supervised manner. 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. We evaluate our methodology in a dynamic environment with discrete time and actions. First with a surprisal minimizing model-free agent (in the RL sense) and then expanding to the model-based case to minimize the expected free energy.

James Goodman, Simon Lucas

Opponent Modelling tries to predict the future actions of opponents, and is required to perform well in multi-player games. There is a deep literature on learning an opponent model, but much less on how accurate such models must be to be useful. We investigate the sensitivity of Monte Carlo Tree Search (MCTS) and a Rolling Horizon Evolutionary Algorithm (RHEA) to the accuracy of their modelling of the opponent in a simple Real-Time Strategy game. We find that in this domain RHEA is much more sensitive to the accuracy of an opponent model than MCTS. MCTS generally does better even with an inaccurate model, while this will degrade RHEA's performance. We show that faced with an unknown opponent and a low computational budget it is better not to use any explicit model with RHEA, and to model the opponent's actions within the tree as part of the MCTS algorithm.

Ivan Bravi, Simon Lucas

In the realm of games research, Artificial General Intelligence algorithms often use score as main reward signal for learning or playing actions. However this has shown its severe limitations when the point rewards are very rare or absent until the end of the game. This paper proposes a new approach based on event logging: the game state triggers an event every time one of its features changes. These events are processed by an Event-value Function (EF) that assigns a value to a single action or a sequence. The experiments have shown that such approach can mitigate the problem of scarce point rewards and improve the AI performance. Furthermore this represents a step forward in controlling the strategy adopted by the artificial agent, by describing a much richer and controllable behavioural space through the EF. Tuned EF are able to neatly synthesise the relevance of the events in the game. Agents using an EF show more robust when playing games with several opponents.

Martin Balla, Simon M. Lucas, Diego Perez-Liebana

The General Video Game Artificial Intelligence (GVGAI) competition has been running for several years with various tracks. 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. This setup poses a difficult challenge for current Reinforcement Learning (RL) algorithms, as they typically require much more data. This work investigates 3 versions of the Advantage Actor-Critic (A2C) algorithm trained on a maximum of 2 levels from the available 5 from the GVGAI framework and compares their performance on all levels. The selected sub-set of games have different characteristics, like stochasticity, reward distribution and objectives. We found that stochasticity improves the generalisation, but too much can cause the algorithms to fail to learn the training levels. The quality of the training levels also matters, different sets of training levels can boost generalisation over all levels. In the GVGAI competition agents are scored based on their win rates and then their scores achieved in the games. We found that solely using the rewards provided by the game might not encourage winning.

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. Where a model is unavailable, a natural aim is to learn a model that reflects accurately the dynamics of the environment. In many situations it might not be possible and minimal glitches in the model may lead to poor performance and failure. This paper explores the problem of model misspecification through uncertainty-aware reinforcement learning agents. We propose a bootstrapped multi-headed neural network that learns the distribution of future states and rewards. We experiment with a number of schemes to extract the most likely predictions. Moreover, we also introduce a global error correction filter that applies high-level constraints guided by the context provided through the predictive distribution. We illustrate our approach on Minipacman. The evaluation demonstrates that when dealing with imperfect models, our methods exhibit increased performance and stability, both in terms of model accuracy and in its use within a planning algorithm.

Jacob Schrum, Jake Gutierrez, Vanessa Volz et al.

Generative Adversarial Networks (GANs) are an emerging form of indirect encoding. The GAN is trained to induce a latent space on training data, and a real-valued evolutionary algorithm can search that latent space. Such Latent Variable Evolution (LVE) has recently been applied to game levels. However, it is hard for objective scores to capture level features that are appealing to players. Therefore, this paper introduces a tool for interactive LVE of tile-based levels for games. The tool also allows for direct exploration of the latent dimensions, and allows users to play discovered levels. The tool works for a variety of GAN models trained for both Super Mario Bros. and The Legend of Zelda, and is easily generalizable to other games. A user study shows that both the evolution and latent space exploration features are appreciated, with a slight preference for direct exploration, but combining these features allows users to discover even better levels. User feedback also indicates how this system could eventually grow into a commercial design tool, with the addition of a few enhancements.

Zhentao Tang, Yuanheng Zhu, Dongbin Zhao et al.

The Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for 2-player video game AI. The challenge arises from the large action space, diverse styles of characters and abilities, and the real-time nature of the game. In this paper, we propose a novel algorithm that combines Rolling Horizon Evolution Algorithm (RHEA) with opponent model learning. The approach is readily applicable to any 2-player video game. 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. The model is learned during the live gameplay. With the learned opponent model, the extended RHEA is able to make more realistic plans based on what the opponent is likely to do. This tends to lead to better results. We compared our approach directly with the bots from the FTGAIC 2018 competition, and found our method to significantly outperform all of them, for all three character. Furthermore, our proposed bot with the policy-gradient-based opponent model is the only one without using Monte-Carlo Tree Search (MCTS) among top five bots in the 2019 competition in which it achieved second place, while using much less domain knowledge than the winner.

Raluca D. Gaina, Sam Devlin, Simon M. Lucas et al.

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. However, the best results in a game are highly dependent on the specific configuration of modifications and hybrids introduced over several papers, each adding additional parameters to the core algorithm. Further, the best previously published parameters have been found from only a few human-picked combinations, as the possibility space has grown beyond exhaustive search. This paper presents the state of the art in Rolling Horizon Evolutionary Algorithms, combining all modifications described in literature, as well as new ones, for a large resultant hybrid. We then use a parameter optimiser, the N-Tuple Bandit Evolutionary Algorithm, to find the best combination of parameters in 20 games from the General Video Game AI Framework. Further, we analyse the algorithm's parameters and some interesting combinations revealed through the optimisation process. Lastly, we find new state of the art solutions on several games by automatically exploring the large parameter space of RHEA.

James Goodman, Simon Lucas

The N-Tuple Bandit Evolutionary Algorithm (NTBEA) has proven very effective in optimising algorithm parameters in Game AI. A potential weakness is the use of a simple average of all component Tuples in the model. This study investigates a refinement to the N-Tuple model used in NTBEA by weighting these component Tuples by their level of information and specificity of match. We introduce weighting functions to the model to obtain Weighted- NTBEA and test this on four benchmark functions and two game environments. These tests show that vanilla NTBEA is the most reliable and performant of the algorithms tested. Furthermore we show that given an iteration budget it is better to execute several independent NTBEA runs, and use part of the budget to find the best recommendation from these runs.

Alexander Dockhorn, Simon M. Lucas, Vanessa Volz et al.

This paper examines learning approaches for forward models based on local cell transition functions. We provide a formal definition of local forward models for which we propose two basic learning approaches. Our analysis is based on the game Sokoban, where a wrong action can lead to an unsolvable game state. Therefore, an accurate prediction of an action's resulting state is necessary to avoid this scenario. In contrast to learning the complete state transition function, local forward models allow extracting multiple training examples from a single state transition. In this way, the Hash Set model, as well as the Decision Tree model, quickly learn to predict upcoming state transitions of both the training and the test set. Applying the model using a statistical forward planner showed that the best models can be used to satisfying degree even in cases in which the test levels have not yet been seen. Our evaluation includes an analysis of various local neighbourhood patterns and sizes to test the learners' capabilities in case too few or too many attributes are extracted, of which the latter has shown do degrade the performance of the model learner.

Raluca D. Gaina, Simon M. Lucas, Diego Perez-Liebana

The space of Artificial Intelligence entities is dominated by conversational bots. Some of them fit in our pockets and we take them everywhere we go, or allow them to be a part of human homes. Siri, Alexa, they are recognised as present in our world. But a lot of games research is restricted to existing in the separate realm of software. We enter different worlds when playing games, but those worlds cease to exist once we quit. 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. But what if they didn't? What if there existed artificial game-players that continuously played games, learned from their experiences and kept getting better? What if they interacted with the real world and us, humans: live-streaming games, chatting with viewers, accepting suggestions for strategies or games to play, forming opinions on popular game titles? In this paper, we introduce the vision behind a new project called Thyia, which focuses around creating a present, continuous, `always-on', interactive game-player.

Cameron Browne, Dennis J. N. J. Soemers, Éric Piette et al.

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. The aim is to provide digital tools and methods to help game historians and other researchers better understand traditional games, their development throughout recorded human history, and their relationship to the development of human culture and mathematical knowledge. This work is being explored in the ERC-funded Digital Ludeme Project. The aim of this inaugural international research meeting on DAL is to gather together leading experts in relevant disciplines - computer science, artificial intelligence, machine learning, computational phylogenetics, mathematics, history, archaeology, anthropology, etc. - to discuss the key themes and establish the foundations for this new field of research, so that it may continue beyond the lifetime of its initiating project.

Rokas Volkovas, Michael Fairbank, John Woodward et al.

There are few digital tools to help designers create game mechanics. A general language to express game mechanics is necessary for rapid game design iteration. The first iteration of a mechanics-focused language, together with its interfacing tool, are introduced in this paper. The language is restricted to two-dimensional, turn-based, tile-based, deterministic, complete-information games. The tool is compared to the existing alternatives for game mechanics prototyping and shown to be capable of succinctly implementing a range of well-known game mechanics.

Ivan Bravi, Simon Lucas, Diego Perez-Liebana et al.

Game-based benchmarks have been playing an essential role in the development of Artificial Intelligence (AI) techniques. Providing diverse challenges is crucial to push research toward innovation and understanding in modern techniques. Rinascimento provides a parameterised partially-observable multiplayer card-based board game, these parameters can easily modify the rules, objectives and items in the game. We describe the framework in all its features and the game-playing challenge providing baseline game-playing AIs and analysis of their skills. We reserve to agents' hyper-parameter tuning a central role in the experiments highlighting how it can heavily influence the performance. The base-line agents contain several additional contribution to Statistical Forward Planning algorithms.

Simon M. Lucas, Alexander Dockhorn, Vanessa Volz et al.

This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a single-player game where the objective can be either to preserve as much life as possible or to extinguish all life as quickly as possible. In order to learn the forward model of the game, we formulate the problem in a novel way that learns the local cell transition function by creating a set of supervised training data and predicting the next state of each cell in the grid based on its current state and immediate neighbours. Using this method we are able to harvest sufficient data to learn perfect forward models by observing only a few complete state transitions, using either a look-up table, a decision tree or a neural network. In contrast, learning the complete state transition function is a much harder task and our initial efforts to do this using deep convolutional auto-encoders were less successful. We also investigate the effects of imperfect learned models on prediction errors and game-playing performance, and show that even models with significant errors can provide good performance.

Simon M. Lucas, Jialin Liu, Ivan Bravi et al.

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. Planet Wars is a real-time strategy game with simple rules but complex game-play. The variant introduced in this paper is designed for speed to enable efficient experimentation, and also for a fixed action space to enable practical inter-operability with General Video Game AI agents. If we treat the game as a win-loss game (which is standard), then this leads to challenging noisy optimisation problems both in tuning agents to play the game, and in tuning game parameters. Here we focus on the problem of tuning an agent, and report results using the recently developed N-Tuple Bandit Evolutionary Algorithm and a number of other optimisers, including Sequential Model-based Algorithm Configuration (SMAC). Results indicate that the N-Tuple Bandit Evolutionary offers competitive performance as well as insight into the effects of combinations of parameter choices.

Simon M. Lucas

This paper describes a new implementation of Planet Wars, designed from the outset for Game AI research. The skill-depth of the game makes it a challenge for game-playing agents, and the speed of more than 1 million game ticks per second enables rapid experimentation and prototyping. The parameterised nature of the game together with an interchangeable actuator model make it well suited to automated game tuning. The game is designed to be fun to play for humans, and is directly playable by General Video Game AI agents.

Ivan Bravi, Jialin Liu, Diego Perez-Liebana et al.

The General Video Game AI competitions have been the testing ground for several techniques for game playing, such as evolutionary computation techniques, tree search algorithms, hyper heuristic based or knowledge based algorithms. So far the metrics used to evaluate the performance of agents have been win ratio, game score and length of games. In this paper we provide a wider set of metrics and a comparison method for evaluating and comparing agents. The metrics and the comparison method give shallow introspection into the agent's decision making process and they can be applied to any agent regardless of its algorithmic nature. In this work, the metrics and the comparison method are used to measure the impact of the terms that compose a tree policy of an MCTS based agent, comparing with several baseline agents. The results clearly show how promising such general approach is and how it can be useful to understand the behaviour of an AI agent, in particular, how the comparison with baseline agents can help understanding the shape of the agent decision landscape. The presented metrics and comparison method represent a step toward to more descriptive ways of logging and analysing agent's behaviours.

Vanessa Volz, Jacob Schrum, Jialin Liu et al.

Generative Adversarial Networks (GANs) are a machine learning approach capable of generating novel example outputs across a space of provided training examples. Procedural Content Generation (PCG) of levels for video games could benefit from such models, especially for games where there is a pre-existing corpus of levels to emulate. This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus. The approach successfully generates a variety of levels similar to one in the original corpus, but is further improved by application of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Specifically, various fitness functions are used to discover levels within the latent space of the GAN that maximize desired properties. Simple static properties are optimized, such as a given distribution of tile types. Additionally, the champion A* agent from the 2009 Mario AI competition is used to assess whether a level is playable, and how many jumping actions are required to beat it. These fitness functions allow for the discovery of levels that exist within the space of examples designed by experts, and also guide the search towards levels that fulfill one or more specified objectives.

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. The algorithm is applied to two game-based hyper-parameter optimisation problems. The N-Tuple system directly models the statistics, approximating the fitness and number of evaluations of each modelled combination of parameters. The model is simple, efficient and informative. Results show that the NTBEA significantly outperforms grid search and an estimation of distribution algorithm.

Simon M. Lucas, Jialin Liu, Diego Pérez-Liébana

The compact genetic algorithm is an Estimation of Distribution Algorithm for binary optimisation problems. Unlike the standard Genetic Algorithm, no cross-over or mutation is involved. Instead, the compact Genetic Algorithm uses a virtual population represented as a probability distribution over the set of binary strings. At each optimisation iteration, exactly two individuals are generated by sampling from the distribution, and compared exactly once to determine a winner and a loser. The probability distribution is then adjusted to increase the likelihood of generating individuals similar to the winner. This paper introduces two straightforward variations of the compact Genetic Algorithm, each of which lead to a significant improvement in performance. The main idea is to make better use of each fitness evaluation, by ensuring that each evaluated individual is used in multiple win/loss comparisons. The first variation is to sample $n>2$ individuals at each iteration to make $n(n-1)/2$ comparisons. The second variation only samples one individual at each iteration but keeps a sliding history window of previous individuals to compare with. We evaluate methods on two noisy test problems and show that in each case they significantly outperform the compact Genetic Algorithm, while maintaining the simplicity of the algorithm.

Simon M. Lucas, Jialin Liu, Diego Pérez-Liébana

A key part of any evolutionary algorithm is fitness evaluation. When fitness evaluations are corrupted by noise, as happens in many real-world problems as a consequence of various types of uncertainty, a strategy is needed in order to cope with this. Resampling is one of the most common strategies, whereby each solution is evaluated many times in order to reduce the variance of the fitness estimates. When evaluating the performance of a noisy optimisation algorithm, a key consideration is the stopping condition for the algorithm. 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. However, this is unrealistic for real-world problems, as if the optimal solution were already known, there would be no need to search for it. This paper argues that the use of First Hitting Time, despite being a commonly used approach, is significantly flawed and overestimates the quality of many algorithms in real-world cases, where the optimum is not known in advance and has to be genuinely searched for. A better alternative is to measure the quality of the solution an algorithm returns after a fixed evaluation budget, i.e., to focus on final solution quality. This paper argues that focussing on final solution quality is more realistic and demonstrates cases where the results produced by each algorithm evaluation method lead to very different conclusions regarding the quality of each noisy optimisation algorithm.

Raluca D. Gaina, Jialin Liu, Simon M. Lucas et al.

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. Online or Rolling Horizon Evolution is one of the options available to evolve sequences of actions for planning in General Video Game Playing, but no research has been done up to date that explores the capabilities of the vanilla version of this algorithm in multiple games. This study aims to critically analyse the different configurations regarding population size and individual length in a set of 20 games from the General Video Game AI corpus. Distinctions are made between deterministic and stochastic games, and the implications of using superior time budgets are studied. Results show that there is scope for the use of these techniques, which in some configurations outperform Monte Carlo Tree Search, and also suggest that further research in these methods could boost their performance.

Joseph Walton-Rivers, Piers R. Williams, Richard Bartle et al.

Agent modelling involves considering how other agents will behave, in order to influence your own actions. In this paper, we explore the use of agent modelling in the hidden-information, collaborative card game Hanabi. We implement a number of rule-based agents, both from the literature and of our own devising, in addition to an Information Set Monte Carlo Tree Search (IS-MCTS) agent. We observe poor results from IS-MCTS, so construct a new, predictor version that uses a model of the agents with which it is paired. We observe a significant improvement in game-playing strength from this agent in comparison to IS-MCTS, resulting from its consideration of what the other agents in a game would do. In addition, we create a flawed rule-based agent to highlight the predictor's capabilities with such an agent.

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. In this paper, we propose for the first time a screen capture learning agent for General Video Game AI framework. A Deep Q-Network algorithm was applied and improved to develop an agent capable of learning to play different games in the framework. After testing this algorithm using various games of different categories and difficulty levels, the results suggest that our proposed screen capture learning agent has the potential to learn many different games using only a single learning algorithm.

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. However, there is little attention paid to population initialization techniques in the setting of general real-time video games. Therefore, this paper proposes the use of population seeding to improve the performance of Rolling Horizon Evolution and presents the results of two methods, One Step Look Ahead and Monte Carlo Tree Search, tested on 20 games of the General Video Game AI corpus with multiple evolution parameter values (population size and individual length). An in-depth analysis is carried out between the results of the seeding methods and the vanilla Rolling Horizon Evolution. In addition, the paper presents a comparison to a Monte Carlo Tree Search algorithm. The results are promising, with seeding able to boost performance significantly over baseline evolution and even match the high level of play obtained by the Monte Carlo Tree Search.

Kamolwan Kunanusont, Raluca D. Gaina, Jialin Liu et al.

This paper describes a new evolutionary algorithm that is especially well suited to AI-Assisted Game Design. The approach adopted in this paper is to use observations of AI agents playing the game to estimate the game's quality. Some of best agents for this purpose are General Video Game AI agents, since they can be deployed directly on a new game without game-specific tuning; these agents tend to be based on stochastic algorithms which give robust but noisy results and tend to be expensive to run. This motivates the main contribution of the paper: the development of the novel N-Tuple Bandit Evolutionary Algorithm, where a model is used to estimate the fitness of unsampled points and a bandit approach is used to balance exploration and exploitation of the search space. Initial results on optimising a Space Battle game variant suggest that the algorithm offers far more robust results than the Random Mutation Hill Climber and a Biased Mutation variant, which are themselves known to offer competitive performance across a range of problems. Subjective observations are also given by human players on the nature of the evolved games, which indicate a preference towards games generated by the N-Tuple algorithm.

Jialin Liu, Julian Togelius, Diego Perez-Liebana et al.

Most games have, or can be generalised to have, a number of parameters that may be varied in order to provide instances of games that lead to very different player experiences. 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. One of the hardest parts of this approach is defining a suitable fitness function. In this paper we explore the possibility of using one of a growing set of General Video Game AI agents to perform automatic play-testing. This enables a very general approach to game evaluation based on estimating the skill-depth of a game. Agent-based play-testing is computationally expensive, so we compare two simple but efficient optimisation algorithms: the Random Mutation Hill-Climber and the Multi-Armed Bandit Random Mutation Hill-Climber. For the test game we use a space-battle game in order to provide a suitable balance between simulation speed and potential skill-depth. Results show that both algorithms are able to rapidly evolve game versions with significant skill-depth, but that choosing a suitable resampling number is essential in order to combat the effects of noise.

Piers R. Williams, Diego Perez-Liebana, Simon M. Lucas

This paper introduces the revival of the popular Ms. Pac-Man Versus Ghost Team competition. We present an updated game engine with Partial Observability constraints, a new Multi-Agent Systems approach to developing Ghost agents and several sample controllers to ease the development of entries. A restricted communication protocol is provided for the Ghosts, providing a more challenging environment than before. The competition will debut at the IEEE Computational Intelligence and Games Conference 2016. Some preliminary results showing the effects of Partial Observability and the benefits of simple communication are also presented.

Jialin Liu, Michael Fairbank, Diego Pérez-Liébana et al.

The OneMax problem is a standard benchmark optimisation problem for a binary search space. Recent work on applying a Bandit-Based Random Mutation Hill-Climbing algorithm to the noisy OneMax Problem showed that it is important to choose a good value for the resampling number to make a careful trade off between taking more samples in order to reduce noise, and taking fewer samples to reduce the total computational cost. This paper extends that observation, by deriving an analytical expression for the running time of the RMHC algorithm with resampling applied to the noisy OneMax problem, and showing both theoretically and empirically that the optimal resampling number increases with the number of dimensions in the search space.

Jialin Liu, Diego Pérez-Liébana, Simon M. Lucas

This paper describes a new algorithm for decision making in two-player real-time video games. As with Monte Carlo Tree Search, the algorithm can be used without heuristics and has been developed for use in general video game AI. The approach is to extend recent work on rolling horizon evolutionary planning, which has been shown to work well for single-player games, to two (or in principle many) player 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. The fitness of each individual is evaluated by playing it against a selection of action-sequences from the opposing population. When choosing an action to take in the game, the first action is chosen from the fittest member of the population for that player. The new algorithm is compared with a number of general video game AI algorithms on three variations of a two-player space battle game, with promising results.

Jialin Liu, Diego Peŕez-Liebana, Simon M. Lucas

The Random Mutation Hill-Climbing algorithm is a direct search technique mostly used in discrete domains. It repeats the process of randomly selecting a neighbour of a best-so-far solution and accepts the neighbour if it is better than or equal to it. In this work, we propose to use a novel method to select the neighbour solution using a set of independent multi- armed bandit-style selection units which results in a bandit-based Random Mutation Hill-Climbing algorithm. The new algorithm significantly outperforms Random Mutation Hill-Climbing in both OneMax (in noise-free and noisy cases) and Royal Road problems (in the noise-free case). The algorithm shows particular promise for discrete optimisation problems where each fitness evaluation is expensive.