Director Agent Brian Magerko University of Michigan.

Slides:



Advertisements
Similar presentations
© Mark E. Damon - All Rights Reserved Another Presentation © All rights Reserved
Advertisements

Artificial Intelligence 2005/06 Partial Order Planning.
CLASSICAL PLANNING What is planning ?  Planning is an AI approach to control  It is deliberation about actions  Key ideas  We have a model of the.
Multiagent Probabilistic Smart Terrain Dr. John R. Sullins Youngstown State University.
1 Soar as a Story Director Brian Magerko University of Michigan.
Web Ontology Language for Service (OWL-S). Introduction OWL-S –OWL-based Web service ontology –a core set of markup language constructs for describing.
Interactive Storytelling Architecture for Training Brian Magerko Bob Wray Additional project contributors: Lisa Holt, Brian Stensrud.
C++ Programming: From Problem Analysis to Program Design, Third Edition Chapter 4: Control Structures I (Selection)
1 Confidence Interval for a Mean. 2 Given A random sample of size n from a Normal population or a non Normal population where n is sufficiently large.
Introduction to Software Design Chapter 1. Chapter 1: Introduction to Software Design2 Chapter Objectives To become familiar with the software challenge.
Functional Requirements – Use Cases Sriram Mohan/Steve Chenoweth (Chapters 14, 21 – Requirements Text) 1.
1 Lecture 7:Control Structures I (Selection) Introduction to Computer Science Spring 2006.
Introduction to Software Design Chapter 1. Chapter 1: Introduction to Software Design2 Chapter Objectives To become familiar with the software challenge.
Story-Line and Drama in Video Games By Greg Brander.
A New Approach to the Design of Interactive Storytelling Engines TeongJoo Ong and John Leggett Texas A&M University.
System Sequence Diagrams
BraMBLe: The Bayesian Multiple-BLob Tracker By Michael Isard and John MacCormick Presented by Kristin Branson CSE 252C, Fall 2003.
© 2007 Tom Beckman Features:  Are autonomous software entities that act as a user’s assistant to perform discrete tasks, simplifying or completely automating.
Swarm Computing Applications in Software Engineering By Chaitanya.
Topics for Today Task planning for non-player characters Coping with player character interactions and their effect on narrative In Hamlet on the Holodeck,
Envision Flow of Execution. ENVISION – Triad of Relationships Policies Intentions Actors Values Landscapes Metrics of Production Provide a common frame.
Bug Localization with Machine Learning Techniques Wujie Zheng
C++ Programming: From Problem Analysis to Program Design, Third Edition Chapter 4: Control Structures I (Selection)
CHAPTER TEN AUTHORING.
Knowledge Representation CPTR 314. The need of a Good Representation  The representation that is used to represent a problem is very important  The.
1 C++ Plus Data Structures Nell Dale Chapter 1 Software Engineering Principles Modified from the Slides made by Sylvia Sorkin, Community College of Baltimore.
Technical Advisor - Mr. Roni Stern Academic Advisor - Dr. Meir Kelah Members: Shimrit Yacobi Yuval Binenboim Moran Lev Lehman Sharon Shabtai.
Artificial Intelligence in Game Design N-Grams and Decision Tree Learning.
Programming Life Cycle Problem analysisunderstand the problem Requirements definition specify what program will do High- and low-level designhow it meets.
University of Windsor School of Computer Science Topics in Artificial Intelligence Fall 2008 Sept 11, 2008.
Decision Making Chapter 7. Definition of Decision Making Characteristics of decision making: a. Selecting a choice from a number of options b. Some information.
Copyright © 2016 Wolters Kluwer Health | Lippincott Williams & Wilkins Chapter 18: Design Considerations for Healthcare Information Systems Chapter 18:
Repetition and Iteration ANSI-C. Repetition We need a control instruction to allows us to execute an statement or a set of statements as many times as.
Tetris Agent Optimization Using Harmony Search Algorithm
Joseph Xu Soar Workshop Learning Modal Continuous Models.
Introduction of Intelligent Agents
Distributed Models for Decision Support Jose Cuena & Sascha Ossowski Pesented by: Gal Moshitch & Rica Gonen.
Computer Game Evaluation Jason Sabada CIS 487 Fall 2006.
DeepDive Model Dongfang Xu Ph.D student, School of Information, University of Arizona Dec 13, 2015.
Decision Making Under Uncertainty CMSC 471 – Spring 2041 Class #25– Tuesday, April 29 R&N, material from Lise Getoor, Jean-Claude Latombe, and.
‘Activity in Context’ – Planning to Keep Learners ‘in the Zone’ for Scenario-based Mixed-Initiative Training Austin Tate, MSc in e-Learning Dissertation.
Game tree search Chapter 6 (6.1 to 6.3 and 6.6) cover games. 6.6 covers state of the art game players in particular. 6.5 covers games that involve uncertainty.
Game AI Matthew Hsieh Meng Tran. Computer Games Many different genres  Action  Role Playing  Adventure  Strategy  Simulation  Sports  Racing Each.
1 CMSC 471 Fall 2004 Class #21 – Thursday, November 11.
Interactive Storytelling via Intelligent Agents By Vincent Vuono CSC3990.
1 CMSC 471 Fall 2002 Class #24 – Wednesday, November 20.
Refining the Use Cases 1. How Use Cases Evolve  Early efforts typically define most of the major use cases.  The refining stages complete the process.
Research Word has a broad spectrum of meanings –“Research this topic on ….” –“Years of research has produced a new ….”
Bellwork March 14, 2016 Copy and answer.. Standard/I can ELAGSE7RL6: Analyze how an author develops and contrasts the points of view of different characters.
Sound Practices of Games Business and Design Presented by Brian Jacobson.
1 Design and evaluation methods: Objectives n Design life cycle: HF input and neglect n Levels of system design: Going beyond the interface n Sources of.
Bob Wray, Charles Newton, Victor Hung, Norb Timpko 7 Jun 2017
Collision Theory and Logic

Chapter 3 of Programming Languages by Ravi Sethi
C++ Plus Data Structures
Collision Theory and Logic
CO Games Development 2 Week 22 Trees
IBM Content and Predictive Analytics for Healthcare How it works
Topics Introduction to Repetition Structures
Escape the Haunted Mansion
Probability and Statistics
Announcements Homework 3 due today (grace period through Friday)
Significance and t testing
Class #20 – Wednesday, November 5
The Alpha-Beta Procedure
Chapter 4: Control Structures I (Selection)
MECH 3550 : Simulation & Visualization
Requirements Engineering Tutorial
Presentation transcript:

Director Agent Brian Magerko University of Michigan

IDA: An Interactive Drama Architecture percepts story content user actions Human player Author AI DirectorHaunt 2: Built in Unreal Tournament AI Actor Interactive game, populated by human-like AI characters with an AI director that dynamically controls an unfolding story. direction

Director Execution Cycle predicted behavior threatens an active plot point all preconds for an active plot point are true new plot- relevant fact timing constraint violated observable game features knowledge execute direction knowledge maintenance plot monitoring set appropriate descriptors as true / false keep track of world state hypothesize entity knowledge model player Haunt 2 environment mark plot points as active / done new plot point has been set as active

Knowledge Maintenance predicted behavior threatens an active plot point all preconds for an active plot point are true new plot- relevant fact timing constraint violated observable game features knowledge execute direction knowledge maintenance plot monitoring set appropriate descriptors as true / false keep track of world state hypothesize entity knowledge model player Haunt 2 environment mark plot points as active / done new plot point has been set as active

Plot Monitoring predicted behavior threatens an active plot point all preconds for an active plot point are true new plot- relevant fact timing constraint violated observable game features knowledge execute direction knowledge maintenance plot monitoring set appropriate descriptors as true / false keep track of world state hypothesize entity knowledge model player Haunt 2 environment mark plot points as active / done new plot point has been set as active

actionspreconditions Plot Representation Location( Sally, x ) Location( Innkeeper, x ) Proximity( Player, Sally, 2) Timing( <=60 ) Talk( Sally, Innkeeper, small_talk) Talk( Innkeeper, Sally, small_talk) timing constraints represent pacing of story flow some plot content is instantiated at run-time postconditions are directions given to synthetic characters partially-ordered with other plot-points Plots ordered for a scene:

Story Direction predicted behavior threatens an active plot point all preconds for an active plot point are true new plot- relevant fact timing constraint violated observable game features knowledge execute direction knowledge maintenance plot monitoring set appropriate descriptors as true / false keep track of world state hypothesize entity knowledge model player Haunt 2 environment mark plot points as active / done new plot point has been set as active All preconditions are met  Perform plot content new goal: small talk

Reactive Direction predicted behavior threatens an active plot point all preconds for an active plot point are true new plot- relevant fact timing constraint violated observable game features knowledge execute direction knowledge maintenance plot monitoring set appropriate descriptors as true / false keep track of world state hypothesize entity knowledge model player Haunt 2 environment mark plot points as active / done new plot point has been set as active new goal: MoveTo(Library) x is unbound User is in library Sally & Innkeeper are in the lounge Time > 60 (constraint violated)  move Sally & Innkeeper

Preemptive Direction predicted behavior threatens an active plot point all preconds for an active plot point are true new plot- relevant fact timing constraint violated observable game features knowledge execute direction knowledge maintenance plot monitoring set appropriate descriptors as true / false keep track of world state hypothesize entity knowledge model player Haunt 2 environment mark plot points as active / done new plot point has been set as active User has been moving to new rooms… Predicted goal: Explore  Predicted timing constraint violation CRASH create sound

appear goto-light goto-sound listenexplore goto-area P(a) = 0.2 P(gs|e) = 0.3P(ga|e) = 0.5 P(l) = 0.2 P(e) = 0.6 P(gl|e) = 0.2 result {Success, 0.42} Single Modeling Run model world state state copy

Probabilistic Player Model … appear goto-lightgoto-sound listenexplore goto-area P(a) = 0.2 P(gs|e) = 0.3P(ga|e) = 0.5 P(l) = 0.2P(e) = 0.6 P(gl|e) = 0.2

Player Prediction Success  Precondition is fulfilled before a timing constraint is violated Failure  Timing constraint is violated Probabilistic sampling Result determines:  if the director preemptively directs  how it directs preemptively

Probabilistic Sampling Model returns a tuple, M  (R, P)  R: success / failure  P: probability of particular sequence of actions chosen Model runs created iteratively until an author- defined limit ρ is reached

Probabilistic Sampling Once modeling is complete, director computes confidence in the user fulfilling plot content  -1 <= C m <= 1  s / f: individual run which yielded a success / failure  P s / f : likelihood of run m occurring C m > α >= 0  success C m < α < 0  insignificant success / failure & preemptive guidance is needed

Connecting Modeling to Director Actions Preemptive direction chosen by score Action scores are a f n of modeling result, C m Director actions rated by a scoring function Score action = (Sub * S action + Eff * E action ) / 2  S action / E action : authored rating for a particular director action  Sub / Eff: weights assigned as a f n of C m

Assigning Score Weights Score for actions computed at run-time:  If 0 < α < C m, then do not preemptively direct  If 0 Eff  If -1 + α < C m < 0, then assign Sub == Eff  If -1 < C m < -1 + α, then assign Sub < Eff α0 1 effectiveness subtlety no direction

Plot Point Choice Story is partially-ordered Which active plot point comes next? Two-tiered approach  Player choice  Heuristic choice

Nuggets and Coal Nuggets  IDA is functionally finished  New theory of story direction  Tells a story (“It works!”)  Has influenced interactive training approaches Coal  Evaluation left to do  Tells a story, just not a great one  Low amount of interaction (“verbs”) in Haunt 2

Questions?