1. Bob Marinier Based on paper by Lehman, Laird, Rosenbloom NSF, DARPA, ONR University of Michigan April 18, 2008

2. 2

3. 3

4. 4

5. Create separate systems for each capability –e.g., language, planning, learning, etc. Create single system of simpler mechanisms out of which these capabilities arise –Cognitive architecture –Inspired by psychology (study of how people think) 5

6. Computer architectures –Differ in processor type, memory size, commands, etc. –Differences reflect designs intended to be optimal under different assumptions about usage 6

7. 7 APPLICATION: word processor TASK: write a paper HARDWARE: PC architecture for content for BEHAVIOR = ARCHITECTURE + CONTENT

8. A theory of the fixed mechanisms and structures that underlie human cognition Said another way: A theory of what is common to the wide array of behaviors we think of as intelligent Soar is one such theory (there are others) –Soar is a computational theory (it actually runs on computers) 8

9. Goal-oriented Takes place in rich, complex, detailed environment Requires a large amount of knowledge Requires use of symbols and abstractions Flexible, and a function of the environment Requires learning from the environment and experience 9

10. 10 Pitcher (Joe) Batter (Sam) First baseman Second baseman Short stop Third baseman Catcher Left-fielder Center-fielder Right-fielder

11. Behaves in goal-oriented manner –Joe’s goal is to win the game –He adopts several subgoals to help him achieve this Operates in a rich, complex, detailed environment –Positions and movements of the players, current state of the game, etc. Uses a large amount of knowledge –Choosing the pitch draws on his own pitching record, Sam’s batting record, etc. Behaves flexibly as a function of the environment –Choosing the pitch takes into account handed-ness of the batter, etc. –When pitch is hit, Joe must change his subgoal to respond to the new situation Uses symbols and abstractions –Since Joe has never played this particular game before, he must draw on previous experience by abstracting away from this day and place Learns from environment and experience –Joe needs to learn from this experience in order to do better when Sam bats in the future 11

12. K1: Knowledge of the objects in the game –E.g., baseball, infield, base line, inning, out, etc. K2: Knowledge of abstract events and particular episodes –E.g., how batters hit, how this guy batted last time K3: Knowledge of rules of the game –E.g., number of outs, balk, infield fly K4: Knowledge of objectives –E.g., get batter out, throw strikes K5: Knowledge of actions or methods for attaining objectives –E.g., use a curve ball, throw to first, walk batter K6: Knowledge of when to choose actions or methods –E.g., if behind in the count, throw a fast ball K7: Knowledge of the component physical actions –E.g., how to throw a curve ball, catch, run 12

13. Knowledge is organized as a sequence of decisions through a problem space 13 Joe is standing on the mound. Sam is at bat. Joe has the goal of getting Sam out. He chooses a curve ball He chooses a fast ball He chooses a slider Strike… Hit Foul… Ball… Strike Hit… Foul Ball… Strike… Single Foul… Homerun Joe faces the next batter He chooses another fast ball He changes to a curve ball He catches it … … … …

14. 14 Initial state f1 v1 f2 v2 S0S0 f1 v1 f2 v1 S1S1 f1 v2 f2 v2 S2S2 f1 v2 f2 v1 S3S3 f1 v5 f2 v1 S 12 f1 v3 f2 v6 S 91 f1 v4 f2 v8 S 30 f1 v2 f2 v6 S 80 … Goal state operator

15. 15 Initial state f1 v1 f2 v2 S0S0 f1 v1 f2 v1 S1S1 f1 v5 f2 v1 S 12 f1 v3 f2 v6 S 91 Goal state operator

16. 16 Current State: batter name Sam batter status not out balls 0 strikes 0 outs 0 … goal batter out problem space pitch Operator: throw-curve

17. How do operators get proposed and compared? –Knowledge determines when an operator is relevant to the current goal and state Joe’s goal is to get the batter out, and he’s the pitcher, so his available operators are kinds of pitches Knowledge represented in the state may influence the choice of pitch (e.g., is the batter right or left handed) 17

18. How are operators selected? –Principle of Rationality “If an agent has knowledge that an operator application will lead to one of its goals then the agent will select that operator” –That is: Rational agents behave in a goal-oriented way 18

19. How is a selected operator applied? –Can execute operator in external world Joe throws a pitch –Can result in internal changes to the state Joe thinks about throwing a pitch –Using states and operators allows us to model both acting and thinking as a function of knowledge 19

20. How do we know if execution of an operator has achieved the goal? –In baseball, rely on knowledge of rules of the game –Can also have external signals (e.g., umpire) How do goals and problem spaces change over time? –Via the application of operators 20

21. So how do we: –Represent knowledge so agent acts in a goal-oriented way? –Represent knowledge in a way that is independent of baseball? Represent knowledge in terms of problem spaces, goals, states, and operators Guide operator choice by the principle of rationality 21

22. What are the architectural processes for using knowledge to create and change states and operators? 22

23. 23 Long-term (Procedural) Memory Short-term (Working) Memory Some knowledge is not specific to the current situation… …and some is

24. 24 Working Memory Procedural Memory Decision Procedure PerceptionAction

25. IF I am the pitcher, the other team is at bat, and I perceive that I am at the mound THEN suggest a goal to get the batter out via pitching (Pitch). IF the problem space is to Pitch and I perceive a new batter who is left/right handed THEN add batter not out, balls 0, strikes 0, and batter left/right- handed to the state. IF the problem space is to Pitch and the batter is not out THEN suggest the throw-curve-ball operator. 25

26. (r1) If I am the pitcher, the other team is at bat, and I perceive that I am at the mound then suggest a goal to get the batter out via pitching (Pitch). (r2) If the problem space is to Pitch and I perceive a new batter who is left/right handed then add batter not out, balls 0, strikes 0, and batter left/right-handed to the state. (r3) If the problem space is to Pitch and the batter is not out then suggest the throw-curve-ball operator. (r4) If the problem space is to Pitch and the batter is not out and the batter is left-handed then suggest the throw-fast-ball operator. (r5) If both throw-fast-ball and throw-curve-ball are suggested then consider throw-curve-ball to be better than throw-fast-ball. (r6) If the throw-curve-ball operator has been selected then send throw-curve to the motor system and add pitch thrown to the state. (r7) If the pitch was thrown and I perceive that it was called a ball, then increment the balls count. (r8) If the pitch was thrown and I perceive that it was called a strike, then increment the strikes count. (r9) If the pitch was thrown and I perceive a hit then add pitch hit to the state 26

27. Each matching rule “maps” from current goal, state and operator to changes to those objects There can be dependencies among rules –Can’t choose a pitch until you’ve decided to pitch to the batter, which you can’t do if you’re not on the mound, etc. –Soar doesn’t recognize dependencies; it just “fires” rules as they match All parts of rules are expressed in terms of perceptions, actions, states and operators 27

28. Elaboration Decide Application Input Output Working Memory Procedural Memory Decision Procedure PerceptionAction

29. 29 Elaboration Decide Application Input Output Procedural Memory (rules) Perception/Action Interface Working Memory Get- batter-out Pitch 0/0 left … New batter Decision Procedure throw-fast throw-curve Throw curve 0/0 left … throw-curve Hit

30. How is (ST) knowledge represented in the state? –As sets of features and values How is general (LT) knowledge represented? –Rules that map one set of feature-values to another What are the architectural processes for using knowledge in LTM? –Decision cycle (input, elaborate, decide, apply, output) What are the mechanisms for interacting with the world? –Perception and action go through interfaces embedded in the decision cycle 30

31. Soar also has ways to deal with a lack of knowledge, including learning Recent work on Soar has focused on new mechanisms to accommodate new kinds of problems –New long-term memories with different properties –New learning mechanisms –Non-symbolic ways of representing knowledge 31

32. Learn from rewards –Reinforcement learning Learn facts –What you know –Semantic memory Learn events –What you remember –Episodic memory Basic drives and … –Emotions, feelings, mood Non-symbolic reasoning –Mental imagery Working memory relevance –Activation Learn from regularities –Spatial and temporal clusters 32 Symbolic Long-Term Memories Procedural Symbolic Short-Term Memory Decision Procedure Chunking Reinforcement Learning Semantic Learning Episodic Learning Perception Action Visual Imagery Feeling Generation Reinforcement Learning Clustering

33. Soar homepage –http://sitemaker.umich.edu/soar/http://sitemaker.umich.edu/soar/ –Read the full Gentle Introduction to Soar –Download Soar and tutorials 28 th Soar Workshop –May 5-7 (Mon-Wed) in Ann Arbor –Invited speakers on Cognitive Robotics Greg Trafton (NRL) and Paul Benjamin (Pace University) –It’s not too late to register! –http://winter.eecs.umich.edu/workshop/http://winter.eecs.umich.edu/workshop/ John Laird’s new book: The Soar Cognitive Architecture (due out Summer 2009) 33