Mutualdiscovery
Our goal is to foster mutual discovery among learners at all stages of cognitive and meta-cognitive growth. Project members take on shifting roles as teacher, student, facilitator, coach, peer and colleague.

Guests are welcome to view our materials. To subscribe, edit, view raw markup, etc., you'll need to register for an account. Accounts are free (and will always be free) - your involvement helps us directly and indirectly (by demonstrating that our work matters to our funders...) StartingPoints has more info.
Mutualdiscovery » IntroAIFall08

Wumpus World

Refer Page 43 from textbook i.e. "figure 2.6" under section 2.3:The Nature of Enviornments (Chapter-2)*

And come up with your own examples just as we did for the PEAS section

Slno Created By Task Environment Observable Deterministic Episodic Static Discrete Agents
1 Micheal Khong Wumpus World Partially Deterministic Sequential Static Discrete Single Agent
2 Farid Nabavi Wumpus World Partially Deterministic Sequential Static Discrete Single
3 Farid Nabavi Automatic Target Recognition Partially Stochastic Sequential Dynamic Continuous Single
4 Shikha Sharma GPS Device Fully Deterministic Episodic Dynamic Continuous Single Agent
5 Soy Joseph Stock Trading : ANN Partially Strategic sequential Dynamic Continuous Multiple Agents
6 Hsien Ern Lan Wumpus World Partially Deterministic sequential Static Discrete Single
7 Devasena Kopparty Soccer Game Fully Stochastic Episodic Dynamic Continuous Multiple Agents
8 Gopikrishna Sinusoidal wave Fully Deterministic sequential Dynamic Continuous Multiple
9 Kavitha Ashwin Cricket (Sports) Fully Strategic Episodic Dynamic Continuous Multiple
10 Jason Sauer Red Light Traffic Camera Fully Stochastic Episodic Dynamic Continuous Single
11 Tapasya Agarwal Real World Partially Stochastic Sequential Dyanamic Continuous multi-agent
12 Sang Nguyen Homing Missile Fully Stochastic Sequential Dynamic Continuous Single
13 Niraj Soni Soccer(Sports) Fully Premeditated Sporadic Dynamic Incessant Multiple
14 Sushant Kadadi Flight Simulator Partially Stochastic Episodic Dynamic Continuous Partially Cooperative Multiagent
15 Paul Trinh My Garmin 770 GPS Fully Deterministic Stochastic Dynamic Continuous Single Agent
16 Kiran Nanjundan Computer Fully Deterministic Sequential Dynamic Continous Single Agent
17 Indraneel Yadav Part-picking robot Partially Strategic Episodic Dynamic Continuous Single Agent
18 Shravani Nimma Backgammon Fully Stochastic Sequential Static Discrete Multiple agent
19 Anup Mohan Wending Machine Partially strategic Sequential Static Continuous Multi-Agent
20 Jyothi Kiran CRO instrument Partially Deterministic Sequential Dynamic Discrete Single Agent
21 Sri Devi Projectile Fully Deterministic Episodic Dynamic Continuous Single Agent
22 Bipin Bitla Bank ATMS Fully Deterministic Episodic Dynamic Continuous Multiple Agents
23 Karthik Sanyasi Wi-Fi Fully Deterministic Episodic Dynamic Continuous Multiple Agents
24 Rahul Pendyal ATM Partially Deterministic Sequential Static Continuous Multiple Agents
25 Kevin Tsai Chess Fully Deterministic Sequential Static Discrete Multiple Agents
26 Anitha padigapati baseball (Sports) Fully Strategic Episodic Dynamic Continuous Multiple

Hilary says, I told you so wink You all fell into a virtual pit! The 7.1 problem is sneakier than it appears, and to get it right, it helps to have the following table first.

Agent Performance Measure Environment Actuators Sensors
Android +1000 (gold), -1000 (pit), -1000 (eaten), -1 (action), -10 (arrow) 4 x 4 grid, start([1,1],right), loc(gold,wumpus)~U([2..4,2..4]), P(pit[2..4,2..4])=0.2 move:(forward,l90,r90), loc(agent) = loc(live wumpus) or loc(pit) then die, forward into wall = bump, grab and loc(gold) gets you gold, shoot continues forward .... stench in loc(wumpus) and directly adjacent, breeze directly adjacent to pit(breeze is either on or off), glitter in loc(gold), bump when walk into wall, wumpus screams when dies, hear all over

Percept are not propositions!

official percept sequence: [ Stench, Breeze, Glitter, Bump, Scream ] also None

names of actions buried in discussion on 197, 198: Grab, Shoot

Created By fully observable* , *partially observable deterministic* , stochastic , *strategic episodic* , *sequential static* , dynamic , *semidynamic discrete*, *continuous single agent, multiagent (competitive, cooperative)
whole class partially it depends on the type of agent (I told you so) - and also capability sequential static (for the moment) discrete single

(originally we called the agent a 'guy', but that led to anthropomorphizing the agent. Look that word up and at it to your personal glossary.

Reports

7.2

* Farid's table driven solution.

* Kavitha's Report on Wumpus World @ "WumpusWorld.ppt"

MutualDiscoveryForm
Mutualdiscdev.CSUEBFall08Courses: IntroAIFall08
r41 - 12 May 2009 - 14:43:47 - HilaryHolz
Guests are welcome to view our materials. To subscribe, edit, view raw markup, etc., you'll need to register for an account. Accounts are free (and will always be free) - your involvement helps us directly and indirectly (by demonstrating that our work matters to our funders...) StartingPoints has more info.
This site is powered by the TWiki collaboration platformCopyright 1999-2010 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Ahatwiki? Send feedback Syndicate this site RSSATOM