Hierarchical Plan Representations for Encoding Strategic Game AI

A wide variety of strategies have been used to create agents in the growing field of real-time strategy AI. However, a frequent problem is the necessity of hand-crafting competencies, which becomes prohibitively difficult in a large space with many corner cases. A preferable approach would be to learn these competencies from the wealth of expert play available. We present a system that uses the Generalized Sequential Pattern (GSP) algorithm from data mining to find common patterns in StarCraft:Brood War replays at both the micro- and macro-level, and verify that these correspond to human understandings of expert play. In the future, we hope to use these patterns to learn tasks and goals in an unsupervised manner for an HTN planner.

Section: Related Workmentioning

confidence: 99%

Sequential Pattern Mining in StarCraft: Brood War for Short and Long-Term Goals

Leece

Jhala

2021

“…While the idea of planning has existed since the beginnings of the field of Artificial Intelligence, planning algorithms have only recently been applied to commercial interactive games: Orkin (2005) employed a STRIPS planner (Fikes, Hart, & Nilsson 1972) to give intelligence to enemies in the first person shooter F.E.A.R.. In the academic realm, HTN planning has been applied to pick strategies for Unreal Tournament bots (Hoang, Lee-Urban, & Munoz-Avila 2005) and Dini et al(2005) provide an overview of various planning algorithms and how the might apply to computer games. Gorniak & Roy has previously employed plan recognition to provide contextual speech understanding in collaborative computer games (Gorniak & Roy 2005;in press) For the game presented here, we use an HTN planning system (Erol, Hendler, & Nau 1994) based on SHOP2 (Nau et al 2003), borrowing elements of the JSHOP2 planner compilation techniques .…”

Section: Related Workmentioning

confidence: 99%

SquadSmart — Hierarchical Planning and Coordinated Plan Execution for Squads of Characters

Gorniak

Davis

2021

This paper presents an application of Hierarchical Task Network (HTN) planning to a squad-based military simulation. The hierarchical planner produces collaborative plans for the whole squad in real time, generating the type of highly coordinated behaviours typical for armed combat situations involving trained professionals. Here, we detail the extensions to HTN planning necessary to provide real-time planning and subsequent collaborative plan execution. To make full hierarchical planning feasible in a game context we employ a planner compilation technique that saves memory allocations and speeds up symbol access. Additionally, our planner can be paused and resumed, making it possible to impose a hard limit on its computation time during any single frame. For collaborative plan execution we describe several synchronization extensions to the HTN framework, allowing agents to participate in several plans at once and to act in parallel or in sequence during single plans. Overall, we demonstrate that HTN planning can be used as an expressive and powerful real-time planning framework for tightly coupled groups of in-game characters.

“…Notable methods include game theory (Emery-Montemerlo, et al 2005), phrasing distributed planning as a constraint satisfaction problem (Yokoo and Hirayama 2000), and distributed POMDPs (Nair et al 2003). Other work has focused on encoding a human's knowledge of a domain into strategies for a team to follow (Hoang, Lee-Urban, and Munoz-Avila 2005)…”

Section: Approaches To Teamworkmentioning

confidence: 99%

Building Robust Planning and Execution Systems for Virtual Worlds

Dini

Lent

Carpenter

et al. 2021

Planning and execution systems have been used in a wide variety of systems to create practical and successful automation. They have been used for everything from performing scientific research on the surface of Mars to controlling enemy characters in video games to performing military air campaign planning. After reviewing past work on these various planning and execution systems, we believe that most lack one or more key components contained in another system. To enable future researchers to build more complete systems, and avoid possible serious system failure, we identify the major technical problems any implementer of such a system would have to face. In addition we cite recent solutions to each of these technical problems. We limit our focus to planning and execution for virtual worlds and the unique problems faced therein.