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

Ontañón, Santiago; Mishra, Kinshuk; Sugandh, Neha; Ram, Ashwin

doi:10.1007/978-3-540-74141-1_12

Cited by 97 publications

(72 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They have become popular because, unlike scripts, they can be created and edited using visual tools, making them much more accessible and understandable to nonprogrammers (Palma et The approach uses cases of actions extracted from annotated game logs to form plans that satisfy goals in Wargus. Adapted from Ontañón et al (2007). 2011). Additionally, their hierarchical structure encourages reuse, as a tree defining a specific behavior can be attached to another tree in multiple positions or can be customized incrementally by adding nodes (Palma et al 2011).…”

Section: Behavior Treesmentioning

confidence: 99%

A Review of Real‐Time Strategy Game AI

Robertson¹,

Watson

2014

AI Magazine

View full text Add to dashboard Cite

Games are an ideal domain for exploring the capabilities of artificial intelligence (AI) within a constrained environment and a fixed set of rules, where problemsolving techniques can be developed and evaluated before being applied to more complex real-world problems (Schaeffer 2001). AI has notably been applied to board games, such as chess, Scrabble, and backgammon, creating competition that has sped the development of many heuristicbased search techniques (Schaeffer 2001). Over the past decade, there has been increasing interest in research based on video game AI, which was initiated by Laird and van Lent (2001) in their call for the use of video games as a test bed for AI research. They saw video games as a potential area for iterative advancement in increasingly sophisticated scenarios, eventually leading to the development of human-level AI. Buro (2003) later called for increased research in real-time strategy (RTS) games as they provide a sandbox for exploring various complex challenges that are central to game AI and many other problems.Video games are an attractive alternative to robotics for AI research because they increasingly provide a complex and realistic environment for simulation, with few of the messy properties (and cost) of real-world equipment (Buro 2004;Laird and van Lent 2001). They also present a number of challenges that set them apart from the simpler board games that AI has famously been applied to in the past. Video games often have real-time constraints that prevent players from thinking extensively about each action, randomness that prevents players from completely planning future events, and hidden information that prevents players from

show abstract

Section: Behavior Treesmentioning

confidence: 99%

A Review of Real‐Time Strategy Game AI

Robertson¹,

Watson

2014

AI Magazine

View full text Add to dashboard Cite

show abstract

“…4) The idea of heterogeneous case bases where cases that contain solutions for several different problems and 5) The introduction of delayed adaptation to deal with dynamic environments. [6] …”

Section: F Case-based Planning and Execution For Real-time Strategy mentioning

confidence: 99%

Incongruity Theory Applied in Dynamic Adaptive Game Artificial Intelligence

Francisco¹,

Ruste²,

Sagum³

et al. 2013

IJFCC

View full text Add to dashboard Cite

Abstract-The Theory of Incongruity is a theory in psychology that states that people create mental concepts about the world in two forms/concepts such as the context and system complexity. The researchers presents an adaptive A.I in which it interacts with a real person and incorporates the theory in order to monitor how the user feels while playing or interacting with the A.I. Two algorithms will be utilized in order to achieve the desired adaptability of the A.I. namely, dynamic scripting and case base reasoning. The goal of the study is to create an A.I. that will be able to react fast and adapt to real human players based on how they feel or what they think regarding the decisions made by the A.I. This study aims to give a player a more thrilling and exciting experience thus, improving the quality of entertainment games provide. The study also focuses on pulling the gamer up the scale in order to improve his skills in game. Giving the player a chance to win by scaling his current skill level but still targeting in the end to win makes the adaptive A.I. more fun to interact with and prove to give a positive reaction or experience to the gamer.Index Terms-Adaptive artificial intelligence, games, theory of incongruity, dynamic scripting.

show abstract

“…The Darmok system [11] is a case-based planning system designed to play the game of WARGUS. Darmok learns plans (cases) by observing a human playing the game, and then reuses such plans combining and adapting them to play new games using case-based planning methods.…”

Section: Case-based Planning and Execution In Wargusmentioning

confidence: 99%

“…In this paper we will focus on the behavior retrieval problem. See [11] for a detailed explanation of the Darmok system.…”

Section: Case-based Planning and Execution In Wargusmentioning

confidence: 99%

See 1 more Smart Citation

Situation Assessment for Plan Retrieval in Real-Time Strategy Games

Mishra

Ontañón

Ram

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Case-Based Planning (CBP) is an effective technique for solving planning problems that has the potential to reduce the computational complexity of the generative planning approaches [8,3]. However, the success of plan execution using CBP depends highly on the selection of a correct plan; especially when the case-base of plans is extensive. In this paper we introduce the concept of a situation and explain a situation assessment algorithm which improves plan retrieval for CBP. We have applied situation assessment to our previous CBP system, Darmok [11], in the domain of real-time strategy games. During Darmok's execution using situation assessment, the high-level representation of the game state i.e. situation is predicted using a decision tree based SituationClassification model. Situation predicted is further used for the selection of relevant knowledge intensive features, which are derived from the basic representation of the game state, to compute the similarity of cases with the current problem. The feature selection performed here is knowledge based and improves the performance of similarity measurements during plan retrieval. The instantiation of the situation assessment algorithm to Darmok gave us promising results for plan retrieval within the real-time constraints.

show abstract

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

Cited by 97 publications

References 6 publications

A Review of Real‐Time Strategy Game AI

A Review of Real‐Time Strategy Game AI

Incongruity Theory Applied in Dynamic Adaptive Game Artificial Intelligence

Situation Assessment for Plan Retrieval in Real-Time Strategy Games

Contact Info

Product

Resources

About