A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking

This paper introduces an information-theoretic method for selecting a small subset of problems which gives us the most information about a group of problem-solving algorithms. This method was tested on the games in the General Video Game AI (GVGAI) framework, allowing us to identify a smaller set of games that still gives a large amount of information about the game-playing agents. This approach can be used to make agent testing more efficient in the future. We can achieve almost as good discriminatory accuracy when testing on only a handful of games as when testing on more than a hundred games, something which is often computationally infeasible. Furthermore, this method can be extended to study the dimensions of effective variance in game design between these games, allowing us to identify which games differentiate between agents in the most complementary ways. As a side effect of this investigation, we provide an up-to-date comparison on agent performance for all GVGAI games, and an analysis of correlations between scores and win-rates across both games and agents.

Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation

Deep reinforcement learning (RL) has shown impressive results in a variety of domains, learning directly from high-dimensional sensory streams. However, when neural networks are trained in a fixed environment, such as a single level in a video game, they will usually overfit and fail to generalize to new levels. When RL models overfit, even slight modifications to the environment can result in poor agent performance. In this paper, we explore how procedurally generated levels during training increase generality. We show that for some games procedural level generation enables generalization to new levels within the same distribution. Additionally, it is possible to achieve better performance with less data by manipulating the difficulty of the levels in response to the performance of the agent. The generality of the learned behaviors is also evaluated on a set of human-designed levels. Our results show that the ability to generalize to human-designed levels highly depends on the design of the level generators. We apply dimensionality reduction and clustering techniques to visualize the generators' distributions of levels and analyze to what degree they can produce levels similar to those designed by a human.

Generative Design in Minecraft (GDMC), Settlement Generation Competition

This paper introduces the settlement generation competition for Minecraft, the first part of the Generative Design in Minecraft challenge. The settlement generation competition is about creating Artificial Intelligence (AI) agents that can produce functional, aesthetically appealing and believable settlements adapted to a given Minecraft map - ideally at a level that can compete with human created designs. The aim of the competition is to advance procedural content generation for games, especially in overcoming the challenges of adaptive and holistic PCG. The paper introduces the technical details of the challenge, but mostly focuses on what challenges this competition provides and why they are scientifically relevant.

General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms

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 to either play multiples 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.

Talakat: Bullet Hell Generation through Constrained Map-Elites

We describe a search-based approach to generating new levels for bullet hell games, which are action games characterized by and requiring avoidance of a very large amount of projectiles. Levels are represented using a domain-specific description language, and search in the space defined by this language is performed by a novel variant of the Map-Elites algorithm which incorporates a feasible- infeasible approach to constraint satisfaction. Simulation-based evaluation is used to gauge the fitness of levels, using an agent based on best-first search. The performance of the agent can be tuned according to the two dimensions of strategy and dexterity, making it possible to search for level configurations that require a specific combination of both. As far as we know, this paper describes the first generator for this game genre, and includes several algorithmic innovations.

Deep Reinforcement Learning for General Video Game AI

The General Video Game AI (GVGAI) competition and its associated software framework provides a way of benchmarking AI algorithms on a large number of games written in a domain-specific description language. While the competition has seen plenty of interest, it has so far focused on online planning, providing a forward model that allows the use of algorithms such as Monte Carlo Tree Search. In this paper, we describe how we interface GVGAI to the OpenAI Gym environment, a widely used way of connecting agents to reinforcement learning problems. Using this interface, we characterize how widely used implementations of several deep reinforcement learning algorithms fare on a number of GVGAI games. We further analyze the results to provide a first indication of the relative difficulty of these games relative to each other, and relative to those in the Arcade Learning Environment under similar conditions.

New And Surprising Ways to Be Mean. Adversarial NPCs with Coupled Empowerment Minimisation

Creating Non-Player Characters (NPCs) that can react robustly to unforeseen player behaviour or novel game content is difficult and time-consuming. This hinders the design of believable characters, and the inclusion of NPCs in games that rely heavily on procedural content generation. We have previously addressed this challenge by means of empowerment, a model of intrinsic motivation, and demonstrated how a coupled empowerment maximisation (CEM) policy can yield generic, companion-like behaviour. In this paper, we extend the CEM framework with a minimisation policy to give rise to adversarial behaviour. We conduct a qualitative, exploratory study in a dungeon-crawler game, demonstrating that CEM can exploit the affordances of different content facets in adaptive adversarial behaviour without modifications to the policy. Changes to the level design, underlying mechanics and our character's actions do not threaten our NPC's robustness, but yield new and surprising ways to be mean.

Playing Atari with Six Neurons

Deep reinforcement learning on Atari games maps pixel directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based on it. Aiming at devoting entire deep networks to decision making alone, we propose a new method for learning policies and compact state representations separately but simultaneously for policy approximation in reinforcement learning. State representations are generated by a novel algorithm based on Vector Quantization and Sparse Coding, trained online along with the network, and capable of growing its dictionary size over time. We also introduce new techniques allowing both the neural network and the evolution strategy to cope with varying dimensions. This enables networks of only 6 to 18 neurons to learn to play a selection of Atari games with performance comparable---and occasionally superior---to state-of-the-art techniques using evolution strategies on deep networks two orders of magnitude larger.

"Press Space to Fire": Automatic Video Game Tutorial Generation

We propose the problem of tutorial generation for games, i.e. to generate tutorials which can teach players to play games, as an AI problem. This problem can be approached in several ways, including generating natural language descriptions of game rules, generating instructive game levels, and generating demonstrations of how to play a game using agents that play in a human-like manner. We further argue that the General Video Game AI framework provides a useful testbed for addressing this problem.

Data-driven Design: A Case for Maximalist Game Design

Maximalism in art refers to drawing on and combining multiple different sources for art creation, embracing the resulting collisions and heterogeneity. This paper discusses the use of maximalism in game design and particularly in data games, which are games that are generated partly based on open data. Using Data Adventures, a series of generators that create adventure games from data sources such as Wikipedia and OpenStreetMap, as a lens we explore several tradeoffs and issues in maximalist game design. This includes the tension between transformation and fidelity, between decorative and functional content, and legal and ethical issues resulting from this type of generativity. This paper sketches out the design space of maximalist data-driven games, a design space that is mostly unexplored.