1 / 15

Mary Lou Maher University of Sydney AAAI AI and Fun Workshop July 2010

Curious Characters in Multiuser Games: A Study in Motivated Reinforcement Learning for Creative Behavior Policies *. Mary Lou Maher University of Sydney AAAI AI and Fun Workshop July 2010.

zihna
Download Presentation

Mary Lou Maher University of Sydney AAAI AI and Fun Workshop July 2010

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Curious Characters in Multiuser Games: A Study in Motivated Reinforcement Learning for Creative Behavior Policies* Mary Lou Maher University of Sydney AAAI AI and Fun Workshop July 2010 1 Based on Merrick, K. and Maher, M.L. (2009) Motivated Reinforcement Learning: Curious Characters for Multiuser Games, Springer.

  2. Outline • Curiosity and Fun • Motivation • Motivated Reinforcement Learning • An Agent Model of a Curious Character • Evaluation of Behavior Policies

  3. Can AI model Fun? Claim: An agent motivated by curiosity to learn patterns is a model of fun.

  4. Games try to achieve flow: a function of the players skill and performance J. Chen, Flow in games (and everything else). Communications of the ACM 50(4):31-34, 2007

  5. Why Motivated Reinforcement Learning? • More efficient learning: • Complement external reward with internal reward • External reward not known at design time • Design tasks • Real world scenrios: Robotics • Virtual world scenarios: NPC in computer games • More autonomy in determining learning tasks • Robotics • NPC in computer games

  6. Models of Motivation • Cognitive: • Interest • Competency • Challenge • Biological • Stasis variables: energy, blood pressure, etc • Social • Conformity • Peer pressure

  7. MRL Agent Model

  8. Motivation as Interesting Events Event is a change in observations: O(t)–O(t’) = (Δ(o1(t), o1(t’)), Δ(o2(t), o2(t’)), … Δ(oL(t), oL(t’)), …) D.E. Berlyne, Exploration and Curiosity, Science 153:24-33, 1966

  9. Sensed States: Context Free Grammar (CFG) CFG = (VS, ΓS, ΨS, S) where: • VS is a set of variables or syntactic categories, • ΓS is a finite set of terminals such that VS ∩ ΓS = {}, • ΨS is a set of productions V -> v where V is a variable and v is a string of terminals and variables,S is the start symbol. Thus, the general form of a sensed state is: • S -> <sensations> • <sensations> -> <PiSensations><sensations> | ε • <PiSensations> -> <sL><PiSensations> | ε • <sL> -> <number> | <string>

  10. MRL for Non Player Characters

  11. Habituated Self Organizing Map

  12. Behavioral Variety • Behavioural variety measures the number of events for which a near optimal policy is learned. • We characterise the level of optimality of a policy learned to achieve the event E(t) in terms of its structural stability.

  13. Behavioral Complexity • The complexity of a policy can be measured by averaging the mean numbers of actions ā E(t) required to repeat E(t) at any time when the current behaviour is stable

  14. Research Directions • Scalability and dynamics: different RL such as decision trees and NN function approximation • Motivation functions: competence, optimal challenges, social models

  15. Relevance to AI and Fun • Is it more fun to play with curious NPC? • Can a curious agent play a game to test how fun a game is?

More Related