Corin Anderson Eric Anderson Geoff Hulten Tessa Lau

Slides:



Advertisements
Similar presentations
Heuristic Search techniques
Advertisements

Ai in game programming it university of copenhagen Reinforcement Learning [Outro] Marco Loog.
Presented by: Analinda Corona
Best-First Search: Agendas
Maximizing the Chance of Winning in Searching Go Game Trees Presenter: Ling Zhao March 16, 2005 Author: Keh-Hsun Chen Accepted by Information Sciences.
UNIVERSITY OF SOUTH CAROLINA Department of Computer Science and Engineering CSCE 580 Artificial Intelligence Problem Spaces and Search Fall 2008 Jingsong.
Term Project User Interface Specifications in a Usability Engineering Course: Challenges and Suggestions Laura Leventhal Julie Barnes Joe Chao Bowling.
Samuvel Johnson nd MCA B. Contents  Introduction to Real-time systems  Two main types of system  Testing real-time software  Difficulties.
Win8 on Intel Programming Course The challenge Paul Guermonprez Intel Software
Stochastic Algorithms Some of the fastest known algorithms for certain tasks rely on chance Stochastic/Randomized Algorithms Two common variations – Monte.
SCRUM for Startups Innosquared – Providing expertise on demand.
Putting together a complete system Chapter 10. Overview  Design a modest but complete system  A collection of objects work together to solve a problem.
Rensselaer Polytechnic Institute Rajagopal Iyengar Combinatorial Approaches to QoS Scheduling in Multichannel Wireless Systems Rajagopal Iyengar Rensselaer.
ANTs PI Meeting, Nov. 29, 2000W. Zhang, Washington University1 Flexible Methods for Multi-agent distributed resource Allocation by Exploiting Phase Transitions.
There’s no such thing as a FreeCiv Marc Friedman Ed Hong Jon Nowitz Steve Wolfman.
Evaluating Teacher Training changing classroom practices Richard Lambert, Ph.D.
Neural and Evolutionary Computing - Lecture 9 1 Evolutionary Neural Networks Design  Motivation  Evolutionary training  Evolutionary design of the architecture.
Chapter 9 Putting together a complete system. This chapter discusses n Designing a complete system. n Overview of the design and implementation process.
ENGH 375 FINAL PROJECT PRESENTATION Sharon O’Boyle May 2014.
Advanced Higher Computing Science
Brief Intro to Machine Learning CS539
Unit 3: Organisations and Behaviour
Principles of Teamwork
sip-identity-04 Added new response codes for various conditions
Click to add text Simple sentence containing the targeted word.
A SMALL TRUTH TO MAKE LIFE 100%
Perfect Squares & Estimating Square Roots
ClassLens Hope C. | Amy L. | Yash T..
Machine Learning Basics
Art of puzzle design Game Genres Rogue Deer Hunter
Announcements Homework 3 due today (grace period through Friday)
Linear Programming CISC4080, Computer Algorithms CIS, Fordham Univ.
A SMALL TRUTH TO MAKE LIFE 100%
CIS 488/588 Bruce R. Maxim UM-Dearborn
A SMALL TRUTH TO MAKE LIFE 100%
A SMALL TRUTH TO MAKE LIFE 100%
Rapid development of Serious Games
CISC5835, Algorithms for Big Data
“Hard” Optimization Problems
Your Notes This presentation AI Home Page (new!) AI Home Page (old!)
Connecting Data with Domain Knowledge in Neural Networks -- Use Deep learning in Conventional problems Lizhong Zheng.
IMPLEMENTATION TEAM STRUCTURE, ROLES, AND RESPONSIBILITIES
Problem Spaces & Search
A SMALL TRUTH TO MAKE LIFE 100%
A SMALL TRUTH TO MAKE LIFE 100%
Proposals & Project Specifications
A SMALL TRUTH TO MAKE LIFE 100%
A SMALL TRUTH TO MAKE LIFE 100%
A SMALL TRUTH TO MAKE LIFE 100%
Computational Models of Discourse Analysis
Us vs. It.
A SMALL TRUTH TO MAKE LIFE 100%
A SMALL TRUTH TO MAKE LIFE 100%
Problem Spaces & Search
A SMALL TRUTH TO MAKE LIFE 100%
Search.
NIEM Tool Strategy Next Steps for Movement
Us vs. It.
A SMALL TRUTH TO MAKE LIFE 100%
A SMALL TRUTH TO MAKE LIFE 100%
A SMALL TRUTH TO MAKE LIFE 100%
Search.
Us vs. It.
A SMALL TRUTH TO MAKE LIFE 100%
A SMALL TRUTH TO MAKE LIFE 100%
A SMALL TRUTH TO MAKE LIFE 100%
Heuristic Search in Empire-Based Games
Perfect Squares Unit 2: Real Numbers
A SMALL TRUTH TO MAKE LIFE 100%
Multidisciplinary Optimization
Presentation transcript:

Corin Anderson Eric Anderson Geoff Hulten Tessa Lau AI in FreeCiv Corin Anderson Eric Anderson Geoff Hulten Tessa Lau

Our Goals Don’t rely on AI’s authors’ knowledge of the game -- learn own strategies Apply “real” AI techniques

Our approach Create a controller for each game element (unit, city, region, army, …) Each controller uses some form of AI Planning, constraint satisfaction, heuristics Different controllers may use different techniques Organize controllers in a hierarchy

Controller hierarchy Master Controller Army Controller Region Controllers non-mil units? all units? only military units? City Controllers should cities boss units around? Unit Controllers

Jobs and tasks Corey Eric Tessa Geoff Army transport controller ; architectural glue Eric City controller ; controller / controller interface Tessa City worker allocation ; UI Geoff Master control -- top-level control

Defining the interface

Example: Settlers

Other examples of three-phase interface

City worker allocation Server-side suggestions are okay But what about maximizing global requirements? Global science, money And what about neighboring city interactions? Land square contention Constraint satisfaction ; integer programming

Army Controller Troop transportation -- a logistics problem Solutions attempted using planning LPSAT: Metric information, such as unit hitpoints, attack value, etc. TGP: Task duration, such as turns to move Showing promise, although some difficulties Really want LPSAT + TGP. Ideas??

Master Controller Approximate FreeCiv with a simpler game Regions Level of Development Level of Exploration Gross Terrain Features Armies Estimate of total offensive/defensive power Location

More Master Controller Simple Actions Armies Move to region (aggressively or passively) Regions - perform a number of actions equal to their development Grow (target region, can be itself or adjacent) Build Army (target to add the units to?) Explore (target region, can be itself or adjacent) Research Evaluation based on development & army size Perform state space search every N turns The effect actions can be hard-coded, learned across games, and/or tuned during the course of a game. The output of this is fed as suggestions into the region and army controllers, does this conform well enough to our suggested master/slave interface?