This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Slide 1
Game Intelligence: The Future Simon M. Lucas Game Intelligence
Group School of CS & EE University of Essex
Slide 2
Meet Adrianne from nVidia
Slide 3
Beautiful, but not very bright, yet.
Slide 4
Game Intelligence Group Main Activity: General purpose
intelligence for game agents 2 Academic staff 1 post-doc 10 PhD
students
Slide 5
Approaches Evolution Reinforcement Learning Monte Carlo Tree
Search
Slide 6
Conventional Game Tree Search Minimax with alpha-beta pruning,
transposition tables Works well when: A good heuristic value
function is known The branching factor is modest E.g. Chess: Deep
Blue, Rybka Tree grows exponentially with search depth
Slide 7
Go Much tougher for computers High branching factor No good
heuristic value function Although progress has been steady, it will
take many decades of research and development before
world-championship calibre go programs exist. Jonathan Schaeffer,
2001
Slide 8
MCTS Operation (fig from CadiaPlayer, Bjornsson and Finsson,
IEEE T-CIAIG) Each iteration starts at the root Follows tree policy
to reach a leaf node Then perform a random roll-out from there Node
N is then added to tree Value of T back- propagated up tree
Slide 9
Upper Confidence Bounds on Trees (UCT) Node Selection Policy
From Kocsis and Szepesvari (2006) Aim: optimal balance between
exploration and exploitation Converges to optimal policy given
infinite number of roll-outs Often not used in practice!
Slide 10
Sample MCTS Tree (fig from CadiaPlayer, Bjornsson and Finsson,
IEEE T-CIAIG)
Slide 11
Learning Tree Policy and Roll-Out Policy Results for Othello
(IEEE CIG 2011)
Slide 12
Research Leadership Grants Conference Series Journal Conference
Special Sessions Competitions Software Toolkits (e.g. WOX, featured
in MSDN Magazine)
Slide 13
Research Grants AI Games Network (EPSRC, 2007 2010; with
Imperial and Bradford) UCT for Games and Beyond (EPSRC, 2010 2014,
joint with Imperial and Bradford; 1.5M total, 489k Essex) Plus IEEE
T-CIAIG Editorial Assistant + Travel
Slide 14
Slide 15
IEEE Transactions on Computational Intelligence and AI in Games
Published quarterly since March 2009 Journal has made an excellent
start
Slide 16
Competitions Many, many competitions Most recent: Ms Pac- Man
versus Ghost Team: IEEE CEC 2011 An interesting and fun AI
challenge Covered by New Scientist, Slashdot etc By Philipp
Rohlfshagen and David Robles
Slide 17
Summary AI + Games Fantastic field to work in The BEST test-bed
for general intelligence Monte-Carlo Tree Search + Reinforcement
Learning: very promising! Reasonable standard general game playing
is already a reality for many games Within the next 10 years well
enjoy interacting with life-like AI characters