Automatic mapping of NES games with mappy

  title={Automatic mapping of NES games with mappy},
  author={Joseph Carter Osborn and Adam James Summerville and Michael Mateas},
  journal={Proceedings of the 12th International Conference on the Foundations of Digital Games},
Game maps are useful for human players, general-game-playing agents, and data-driven procedural content generation. These maps are generally made by hand-assembling manually-created screen-shots of game levels. Besides being tedious and error-prone, this approach requires additional effort for each new game and level to be mapped. The results can still be hard for humans or computational systems to make use of, privileging visual appearance over semantic information. We describe a software… 

Figures from this paper

MappyLand: Fast, Accurate Mapping for Console Games

We present MappyLand, a rewrite and enhancement of the earlier Mappy automatic game mapping system, which leverages instrumentation of a game console emulator to produce, from a sequence of game

Taking the Scenic Route: Automatic Exploration for Videogames

It is shown that off-the-shelf automatic exploration strategies can explore with an effectiveness comparable to human gameplay on the same timescale, and generic methods for quantifying exploration quality as a function of time are contributed.

Game Studies at Scale: Towards Facilitating Exploration of Game Corpora

It is argued that appropriate software tools can support research in game studies, allowing individual games to be read at the level of gameplay as well as the implementation level, and permit analysis to scale in a similar fashion as distant reading allows for traditional texts.

Conceptual Game Expansion

This article learns representations of existing games from gameplay video and uses these to approximate a search space of novel games, and demonstrates that these novel games are indistinguishable from human games in terms of challenge and challenge and that one of the novel games was equivalent toone of the human gamesIn terms of fun, frustration, and likeability.

AtDELFI: automatically designing legible, full instructions for games

The findings suggest that a graph representation scheme works well for simple arcade style games such as Space Invaders and Pacman, but it appears that tutorials for more complex games might require higher-level understanding of the game than just single mechanics.

Automatic Critical Mechanic Discovery in Video Games

The proposed method of automatic critical mechanic discovery for video games using a combination of game description parsing and playtrace information shows either matched or improved performance over the old method, demonstrating that play Trace information is responsible for more complete critical mechanics discovery.

The Videogame Affordances Corpus

This work presents a schema, annotation tool, and dataset for codifying screenshots containing game objects in terms of their affordances, suitable for AI agents and machine learning algorithms for a variety of interesting and significant games.

Towards General RPG Playing

The motivation behind general RPG playing in a sub-domain of Nintendo Entertainment System (NES) RPGs, some promising approaches to some of its fundamental issues, and immediate next steps are described, including a few concrete benchmark problems on the path towards automated play of these complex games.

Generating levels that teach mechanics

This paper evolves small levels for the Mario AI Framework that can only be beaten by an agent that knows how to perform specific actions in the game.

Automated Game Design via Conceptual Expansion

This paper introduces a method for recombining existing games to create new games through a process called conceptual expansion, and represents the first machine learning-based automated game design system.



Text-based adventures of the golovin AI agent

This paper uses genre-related corpora to create language models suitable to the domain of text-based adventure games, and embeds mechanisms that allow the agent to specify, and separately handle, important tasks as fighting opponents, managing inventory, and navigating on the game map.

Procedural Content Generation via Machine Learning (PCGML)

This paper addresses the relatively new paradigm of using machine learning (in contrast with search-based, solver- based, and constructive methods), and focuses on what is most often considered functional game content, such as platformer levels, game maps, interactive fiction stories, and cards in collectible card games.

The VGLC: The Video Game Level Corpus

A corpora of video game levels in an easy to parse format ideal for different machine learning and other game AI research purposes is made available.

Game Level Generation from Gameplay Videos

We present an unsupervised process to generate full video game levels from a model trained on gameplay video. The model represents probabilistic relationships between shapes properties, and

Mechanics automatically recognized via interactive observation: jumping

A modified Nintendo Entertainment System (NES) emulator is used to semi-automatically run experiments on a large subset of NES platform games, and models of jumps from different developers, series, and games across the history of the console are built.

Game Engine Learning from Video

This work presents a novel approach to learn a forward simulation model via simple search over pixel input and demonstrates the significant improvement in predicting future states compared with a baseline CNN and applies the learned model to train a game playing agent.

Refining operational logics

This paper provides an explicit and detailed definition of operational logics; specifies a set of logics which seems fundamental and suffices to interpret a broad variety of games across several genres; gives the first detailed explanation of how exactly operationallogics combine.

Curiosity Search: Producing Generalists by Encouraging Individuals to Continually Explore and Acquire Skills throughout Their Lifetime

It is revealed that when modified to encourage intra-life behavioral diversity, Novelty Search can produce organisms that explore almost as much of their environment as Curiosity Search, although Curiosity Search retains a significant performance edge.

Curiosity-Driven Exploration by Self-Supervised Prediction

This work forms curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model, which scales to high-dimensional continuous state spaces like images, bypasses the difficulties of directly predicting pixels, and ignores the aspects of the environment that cannot affect the agent.

Rog-O-Matic : a belligerent expert system

The major features of the Rog-O-Matic system, the types of knowledge sources and rules used to control the exploration, and the performance of the system with human Rogue players are presented.