DOC PREVIEW
Berkeley COMPSCI 188 - Lecture 26: Conclusion

This preview shows page 1-2-3 out of 10 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

1CS 188: Artificial IntelligenceFall 2010Lecture 26: Conclusion12/2/2010Dan Klein – UC BerkeleyPacman Contest Challenges: Long term strategy Multiple agents Adversarial utilities Uncertainty about other agents’ positions, plans, etc.22Pacman Contest 50 teams Creative names: ConditionalIndependenceDay, NoPlaceLike127001, … Creative methods: tracking, learning, search… 50 qualifiers (a third of the class!) XYZ achievements Amazing work by everyone! Final Tournament … Final matches: now!3Finalists43For Third Place5For First / Second Place64…and Congratulations to All! Amazing work by everyone Record number of entries (60 teams) Record number of qualifications (45!) Lots of mutual support on newsgroup / office hours… You should all be proud of what you’ve accomplished!7Example: Starcraft85What is Starcraft?9Image from Ben WeberWhy is Starcraft Hard? Starcraft is: Adversarial Long Horizon Partially Observable Realtime Concurrent … No single algorithm (e.g. minimax) will solve it off-the-shelf106The Berkeley Overmind11Search: path planningMinimax: targetingLearning: micro controlInference: tracking unitsScheduling: resource managementHierarchical controlhttp://overmind.eecs.berkeley.eduSearch for Pathing12[Pathing]7Minimax for Targeting13[Targeting]RL for Micro Control14[RL, Potential Fields]8Inference / VPI / Scouting15[Scouting, Cloaking]AIIDE 2010 Competition169Pacman: Beyond Simulation?Students at Colorado University: http://pacman.elstonj.com[DEMO]Bugman? AI = Animal Intelligence? Wim van Eck at Leiden University Pacman controlled by a human Ghosts controlled by crickets Vibrations drive crickets toward or away from Pacman’s locationhttp://pong.hku.nl/~wim/bugman.htm[DEMO]1810Where to go next? Congratulations, you’ve seen the basics of modern AI … and done some amazing work putting it to use! How to continue: Machine learning: cs281a / cs281b Cognitive modeling: cog sci 131 Vision: cs280 Robotics: cs287 NLP: cs288 Decision making: cs289 … and more; ask if you’re interested Next term: cs194 (Starcraft, not yet in telebears) cs288 (focus on MT for SP11) maybe one other grad class TBA (cs289?)19That’s It! Help us out with some course evaluations Have a good break, and always maximize your expected


View Full Document

Berkeley COMPSCI 188 - Lecture 26: Conclusion

Documents in this Course
CSP

CSP

42 pages

Metrics

Metrics

4 pages

HMMs II

HMMs II

19 pages

NLP

NLP

23 pages

Midterm

Midterm

9 pages

Agents

Agents

8 pages

Lecture 4

Lecture 4

53 pages

CSPs

CSPs

16 pages

Midterm

Midterm

6 pages

MDPs

MDPs

20 pages

mdps

mdps

2 pages

Games II

Games II

18 pages

Load more
Download Lecture 26: Conclusion
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Lecture 26: Conclusion and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Lecture 26: Conclusion 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?