CS343 Artificial Intelligence

Transcription

1 CS343 Artificial Intelligence Prof: Department of Computer Science The University of Texas at Austin

2 Good Morning, Colleagues

3 Good Morning, Colleagues Are there any questions?

4 Logistics Questions about the syllabus?

5 Logistics Questions about the syllabus? Class registration

6 Logistics Questions about the syllabus? Class registration Problems with the assignment?

7 Logistics Questions about the syllabus? Class registration Problems with the assignment? Piazza useful discussion yesterday

8 Logistics Questions about the syllabus? Class registration Problems with the assignment? Piazza useful discussion yesterday CC Kim and me on everything

9 Logistics Questions about the syllabus? Class registration Problems with the assignment? Piazza useful discussion yesterday CC Kim and me on everything Assignments up through week 3

10 Logistics Questions about the syllabus? Class registration Problems with the assignment? Piazza useful discussion yesterday CC Kim and me on everything Assignments up through week 3

11 Example Intelligent (autonomous) Agents Autonomous robot

12 Example Intelligent (autonomous) Agents Autonomous robot Information gathering agent Find me the cheapest?

13 Example Intelligent (autonomous) Agents Autonomous robot Information gathering agent Find me the cheapest? E-commerce agents Decides what to buy/sell and does it

14 Example Intelligent (autonomous) Agents Autonomous robot Information gathering agent Find me the cheapest? E-commerce agents Decides what to buy/sell and does it Air-traffic controller

15 Example Intelligent (autonomous) Agents Autonomous robot Information gathering agent Find me the cheapest? E-commerce agents Decides what to buy/sell and does it Air-traffic controller Meeting scheduler

16 Example Intelligent (autonomous) Agents Autonomous robot Information gathering agent Find me the cheapest? E-commerce agents Decides what to buy/sell and does it Air-traffic controller Meeting scheduler Computer-game-playing agent

17 Not Intelligent Agents Thermostat Telephone Answering machine Pencil Java object

18 Environments Environment = sensations, actions

19 Environments Environment = sensations, actions fully observable vs. partially observable (accessible)

20 Environments Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent

21 Environments Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic)

22 Environments Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic) episodic vs. sequential

23 Environments Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic) episodic vs. sequential static vs. dynamic

24 Environments Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic) episodic vs. sequential static vs. dynamic discrete vs. continuous

25 Environments Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic) episodic vs. sequential static vs. dynamic discrete vs. continuous known vs. unknown

26 Student Examples game bot robot waiter bowling robot, ping pong player kiva robots, Mars rover, robot suturing agent Wall-E Words with friends word checker thermostat trading agent Siri Briggo piano playing agent unhappiness agent

27 BE a learning agent

28 BE a learning agent You, as a group, act as a learning agent

29 BE a learning agent You, as a group, act as a learning agent Actions: Wave, Stand, Clap

30 BE a learning agent You, as a group, act as a learning agent Actions: Wave, Stand, Clap Observations: colors, reward

31 BE a learning agent You, as a group, act as a learning agent Actions: Wave, Stand, Clap Observations: colors, reward Goal: Find an optimal policy

32 BE a learning agent You, as a group, act as a learning agent Actions: Wave, Stand, Clap Observations: colors, reward Goal: Find an optimal policy Way of selecting actions that gets you the most reward

33 How did you do it?

34 How did you do it? What is your policy? What does the world look like?

35 How did you do it? What is your policy? What does the world look like? +1 1 Stand Clap +2 1 Wave 1 1

36 Formalizing what Just Happened Knowns:

37 Formalizing what Just Happened Knowns: O = {Blue, Red, Green, Black,...} Rewards in IR A = {W ave, Clap, Stand} o 0, a 0, r 0, o 1, a 1, r 1, o 2,...

38 Formalizing what Just Happened Knowns: O = {Blue, Red, Green, Black,...} Rewards in IR A = {W ave, Clap, Stand} o 0, a 0, r 0, o 1, a 1, r 1, o 2,... Unknowns:

39 Formalizing what Just Happened Knowns: O = {Blue, Red, Green, Black,...} Rewards in IR A = {W ave, Clap, Stand} o 0, a 0, r 0, o 1, a 1, r 1, o 2,... Unknowns: S = 4x3 grid R : S A IR P = S O T : S A S

40 Formalizing what Just Happened Knowns: O = {Blue, Red, Green, Black,...} Rewards in IR A = {W ave, Clap, Stand} o 0, a 0, r 0, o 1, a 1, r 1, o 2,... Unknowns: S = 4x3 grid R : S A IR P = S O T : S A S o i = P(s i )

41 Formalizing what Just Happened Knowns: O = {Blue, Red, Green, Black,...} Rewards in IR A = {W ave, Clap, Stand} o 0, a 0, r 0, o 1, a 1, r 1, o 2,... Unknowns: S = 4x3 grid R : S A IR P = S O T : S A S o i = P(s i ) r i = R(s i, a i )

42 Formalizing what Just Happened Knowns: O = {Blue, Red, Green, Black,...} Rewards in IR A = {W ave, Clap, Stand} o 0, a 0, r 0, o 1, a 1, r 1, o 2,... Unknowns: S = 4x3 grid R : S A IR P = S O T : S A S o i = P(s i ) r i = R(s i, a i ) s i+1 = T (s i, a i )

43 Describe the environment Environment = sensations, actions

44 Describe the environment Environment = sensations, actions fully observable vs. partially observable (accessible)

45 Describe the environment Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent

46 Describe the environment Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic)

47 Describe the environment Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic) episodic vs. sequential

48 Describe the environment Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic) episodic vs. sequential static vs. dynamic

49 Describe the environment Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic) episodic vs. sequential static vs. dynamic discrete vs. continuous

50 Describe the environment Environment = sensations, actions fully observable vs. partially observable (accessible) single-agent vs. multiagent deterministic vs. non-deterministic (stochastic) episodic vs. sequential static vs. dynamic discrete vs. continuous known vs. unknown

51 Next week: Search Textbook readings Responses both Monday and Wednesday Python tutorial due