Situation Assessment for Plan Retrieval in Real-Time Strategy Games

Abstract

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.

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

“…In their work, they used human demonstration to learn plans, which are then composed at run-time in order to form full-fledges strategies to play the game. In [10] they improve over their previous CBP approach by using situation assessment for improving the quality and speed of plan retrieval. Hierarchical Task-Network (HTN) planning has also been explored with some success in the context of simpler first-person shooter games [11].…”

“…• AIUR 10 : is mainly divide-and-conquer oriented, with a slight abstraction on economy due to a SpendManager deciding how to spend and share resources among Base, Production and Construction Managers. At the beginning of a game, the MoodManager initializes a "mood" which will influence both tactics and strategy.…”

Special tactics: A Bayesian approach to tactical decision-making

“…A case based behavior generator spawn missing goals which are missing from the current state and plan according to the recognized state. In [8], [9], they used a knowledge-based approach to perform situation assessment to use the right plan, performing runtime adaptation by monitoring its performance. Sharma et al [10] combined CBR and reinforcement learning to enable reuse of tactical plan components.…”

“…It can be used in production thanks to its low CPU and memory footprint. The dataset, its documentation 8 , as well as our model implementation 9 (and other data-exploration tools) are free software and can be found online. We plan to use this model in our StarCraft AI competition entry bot as it gives our bot tactical autonomy and a way to adapt to our opponent.…”

A Bayesian model for opening prediction in RTS games with application to StarCraft

“…Ontañón et al [6] base their real-time case-based planning (CBP) system on a plan dependency graph which is learned from human demonstration. In [7], [12], they use CBR and expert demonstrations on Wargus. They improve the speed of CPB by using a decision tree to select relevant features.…”