Santiago Ontañón

A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft

This paper presents an overview of the existing work on AI for real-time strategy (RTS) games. Specifically, we focus on the work around the game StarCraft, which has emerged in the past few years as the unified test bed for this research. We describe the specific AI challenges posed by RTS games, and overview the solutions that have been explored to address them. Additionally, we also present a summary of the results of the recent StarCraft AI competitions, describing the architectures used by the participants. Finally, we conclude with a discussion emphasizing which problems in the context of RTS game AI have been solved, and which remain open.

Case-Based Planning and Execution for Real-Time Strategy Games

Artificial Intelligence techniques have been successfully applied to several computer games. However in some kinds of computer games, like real-time strategy (RTS) games, traditional artificial intelligence techniques fail to play at a human level because of the vast search spaces that they entail. In this paper we present a real-time case based planning and execution approach designed to deal with RTS games. We propose to extract behavioral knowledge from expert demonstrations in form of individual cases. This knowledge can be reused via a case based behavior generator that proposes behaviors to achieve the specific open goals in the current plan. Specifically, we applied our technique to the W ARGUS domain with promising results.

Learning and joint deliberation through argumentation in multiagent systems

In this paper we will present an argumentation framework for learning agents (AMAL) designed for two purposes: (1) for joint deliberation, and (2) for learning from communication. The AMAL framework is completely based on learning from examples: the argument preference relation, the argument generation policy, and the counterargument generation policy are case-based techniques. For join deliberation, learning agents share their experience by forming a committee to decide upon some joint decision. We experimentally show that the argumentation among committees of agents improves both the individual and joint performance. For learning from communication, an agent engages into arguing with other agents in order to contrast its individual hypotheses and receive counterexamples; the argumentation process improves their learning scope and individual performance.

DRAMA MANAGEMENT AND PLAYER MODELING FOR INTERACTIVE FICTION GAMES

A growing research community is working toward employing drama management components in story‐based games. These components gently guide the story toward a narrative arc that improves the players gaming experience. In this article we evaluate a novel drama management approach deployed in an interactive fiction game called Anchorhead. This approach uses players feedback as the basis for guiding the personalization of the interaction. The results indicate that adding our Case‐based Drama manaGer (C‐DraGer) to the game guides the players through the interaction and provides a better overall player experience. Unlike previous approaches to drama management, this article focuses on exhibiting the success of our approach by evaluating results using human players in a real game implementation. Based on this work, we report several insights on drama management which were possible only due to an evaluation with real players.

Ensemble Case-Based Reasoning: Collaboration Policies for Multiagent Cooperative CBR

Multiagent systems offer a new paradigm to organize AI applications. Our goal is to develop techniques to integrate CBR into applications that are developed as multiagent systems. CBR offers the multiagent systems paradigm the capability of autonomously learning from experience. In this paper we present a framework for collaboration among agents that use CBR and some experiments illustrating the framework. We focus on three collaboration policies for CBR agents: Peer Counsel, Bounded Counsel and Committee policies. The experiments show that the CBR agents improve their individual performance collaborating with other agents without compromising the privacy of their own cases. We analyze the three policies concerning accuracy, cost, and robustness with respect to number of agents and case base size.

Amalgams: a formal approach for combining multiple case solutions

How to reuse or adapt past solutions to new problems is one of the least understood problems in case-based reasoning. In this paper we will focus on the problem of how to combine solutions coming from multiple cases in search-based approaches to reuse. For that purpose, we introduce the notion of amalgam. Assuming the solution space can be characterized as a generalization space, an amalgam of two solutions is a third solution which combines as much as possible from the original two solutions. In the paper we define amalgam as a formal operation over terms in a generalization space, and we discuss how amalgams may be applied in search-based reuse techniques to combine case solutions.

The Explanatory Power of Symbolic Similarity in Case-Based Reasoning

A desired capability of automatic problem solvers is that they can explain the results. Such explanations should justify that the solution proposed by the problem solver arises from the known domain knowledge. In this paper we discuss how explanations can be used in case-based reasoning (CBR) in order to justify the results in classification tasks and also for solving new problems. We particularly focus on explanations derived from building a symbolic description of the similar aspects among cases. Moreover, we show how symbolic descriptions of similarity can be exploited in the different processes of CBR, namely retrieve, reuse, revise, and retain.

Similarity measures over refinement graphs

Similarity also plays a crucial role in support vector machines. Similarity assessment plays a key role in lazy learning methods such as k-nearest neighbor or case-based reasoning. In this paper we will show how refinement graphs, that were originally introduced for inductive learning, can be employed to assess and reason about similarity. We will define and analyze two similarity measures, Sλ and Sπ, based on refinement graphs. The anti-unification-based similarity, Sλ, assesses similarity by finding the anti-unification of two instances, which is a description capturing all the information common to these two instances. The property-based similarity, Sπ, is based on a process of disintegrating the instances into a set of properties, and then analyzing these property sets. Moreover these similarity measures are applicable to any representation language for which a refinement graph that satisfies the requirements we identify can be defined. Specifically, we present a refinement graph for feature terms, in which several languages of increasing expressiveness can be defined. The similarity measures are empirically evaluated on relational data sets belonging to languages of different expressiveness.

Learning from Demonstration and Case-Based Planning for Real-Time Strategy Games

Artificial Intelligence (AI) techniques have been successfully applied to several computer games. However, in the vast majority of computer games traditional AI techniques fail to play at a human level because of the characteristics of the game. Most current commercial computer games have vast search spaces in which the AI has to make decisions in real-time, thus rendering traditional search based techniques inapplicable. For that reason, game developers need to spend a big effort in hand coding specific strategies that play at a reasonable level for each new game. One of the long term goals of our research is to develop artificial intelligence techniques that can be directly applied to such domains, alleviating the effort required by game developers to include advanced AI in their games.

Arguments and Counterexamples in Case-Based Joint Deliberation

Multiagent learning can be seen as applying ML techniques to the core issues of multiagent systems, like communication, coordination, and competition. In this paper, we address the issue of learning from communication among agents circumscribed to a scenario with two agents that (1) work in the same domain using a shared ontology, (2) are capable of learning from examples, and (3) communicate using an argumentative framework. We will present a two fold approach consisting of (1) an argumentation framework for learning agents, and (2) an individual policy for agents to generate arguments and counterarguments (including counterexamples). We focus on argumentation between two agents, presenting (1) an interaction protocol (AMAL2) that allows agents to learn from counterexamples and (2) a preference relation to determine the joint outcome when individual predictions are in contradiction. We present several experiment to asses how joint predictions based on argumentation improve over individual prediction.