Game AI Competitions: Motivation for the Imitation Game-Playing Competition

@article{Swiechowski2020GameAC,
  title={Game AI Competitions: Motivation for the Imitation Game-Playing Competition},
  author={Maciej Swiechowski},
  journal={2020 15th Conference on Computer Science and Information Systems (FedCSIS)},
  year={2020},
  pages={155-160}
}
  • M. Swiechowski
  • Published 1 September 2020
  • Computer Science
  • 2020 15th Conference on Computer Science and Information Systems (FedCSIS)
Games have played crucial role in advancing research in Artificial Intelligence and tracking its progress. In this article, a new proposal for game AI competition is presented. The goal is to create computer players which can learn and mimic the behavior of particular human players given access to their game records. We motivate usefulness of such an approach in various aspects, e.g., new ways of understanding what constitutes the human-like AI or how well it fits into the existing game… 

Figures from this paper

Team Sports for Game AI Benchmarking Revisited
TLDR
It is argued that, in spite of the rise of increasingly more sophisticated game genres, team sport games will remain an important testbed for AI benchmarking due to two primary factors: genre-specific challenges for AI systems and unmistakable nonskill-related goals of AI systems contributing to player enjoyment.
Computing Games: Bridging the Gap Between Search and Entertainment
TLDR
The probability-based proof number search (PPNS) and single conspiracy number (SCN) were used as the domain-independent indicators to analyze how uncertainty affects various game elements and demonstrate the link between the search indicators and the measure of entertainment where uncertainty plays a vital role in both contexts.
StarCraft strategy classification of a large human versus human game replay dataset
TLDR
This work focuses on early to mid-game strategies in matches less than 15 minutes long in Starcraft: Brood War, and labels the files of the dataset and makes the labeled dataset available.
Monte Carlo Tree Search: A Review of Recent Modifications and Applications
TLDR
In more complex games (e.g. those with a high branching factor or real-time ones), an efficient MCTS application often requires its problem-dependent modification or integration with other techniques and domain-specific modifications and hybrid approaches are the main focus of this survey.
Deep Learning and Artificial General Intelligence: Still a Long Way to Go
TLDR
This article approaches this statement critically showing major reasons of why deep neural networks, as of the current state, are not ready to be the technique of choice for reaching AGI.
Introducing LogDL – Log Description Language for Insights from Complex Data
We propose a new logic-based language called Log Description Language (LogDL), designed to be a medium for the knowledge discovery workflows over complex data sets. It makes it possible to operate

References

SHOWING 1-10 OF 56 REFERENCES
General Game Playing: Overview of the AAAI Competition
TLDR
An overview of the technical issues and logistics associated with this summer's competition, as well as the relevance of general game playing to the long range-goals of artificial intelligence, are overviewed.
Specialized vs. Multi-game Approaches to AI in Games
TLDR
This work concludes on what defines a successful player, which has been using a minimal knowledge and a mechanism called Monte Carlo Tree-Search, which is simulation-based and self-improving over time.
The 2014 General Video Game Playing Competition
TLDR
All controllers submitted to the first General Video Game Playing Competition are described, with an in-depth description of four of them by their authors, including the winner and the runner-up entries of the contest.
Recent Advances in General Game Playing
TLDR
Recent progress in the most challenging research areas of Artificial Intelligence (AI) related to universal game playing is reviewed, including Monte-Carlo Tree Search and its enhancements.
Blood Bowl: A New Board Game Challenge and Competition for AI
TLDR
The Fantasy Football AI (FFAI) framework is presented, that implements the core rules of Blood Bowl and includes a forward model, several OpenAI Gym environments for reinforcement learning, competition functionalities, and a web application that allows for human play.
Self-Adaptation of Playing Strategies in General Game Playing
TLDR
This paper presents a GGP player which managed to win four out of seven games in the 2012 preliminary round and advanced to the final phase and discusses the efficacy of proposed playing strategies and evaluates the mechanism of their switching.
A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft
TLDR
An overview of the existing work on AI for real-time strategy (RTS) games focuses on the work around the game StarCraft, which has emerged in the past few years as the unified test bed for this research.
Granular Games in Real-Time Environment
TLDR
It is suggested to follow the paradigms of information granulation and re-define states/actions at a higher level of abstraction, so the MCTS algorithms can operate on more general concepts, which reflect the creators' domain knowledge.
Self-Play for Training General Fighting Game AI
TLDR
This paper trains a general fighting game AI from self-play games to outperform an unseen opponent AI and shows that it is more effective to use a variety of AIs with different behaviors as training partners.
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
TLDR
This paper generalizes the AlphaZero approach into a single AlphaZero algorithm that can achieve superhuman performance in many challenging games, and convincingly defeated a world champion program in the games of chess and shogi (Japanese chess), as well as Go.
...
...