1 / 38

CS 188: Artificial Intelligence Spring 2007

CS 188: Artificial Intelligence Spring 2007. Lecture 21:Reinforcement Learning: I Utilities and Simple decisions 4/10/2007. Srini Narayanan – ICSI and UC Berkeley. Announcments. Othello tournament signup Please send email to cs188@imail.berkeley.edu HW on classification out today

acardenas
Download Presentation

CS 188: Artificial Intelligence Spring 2007

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. CS 188: Artificial IntelligenceSpring 2007 Lecture 21:Reinforcement Learning: I Utilities and Simple decisions 4/10/2007 Srini Narayanan – ICSI and UC Berkeley

  2. Announcments • Othello tournament signup • Please send email to cs188@imail.berkeley.edu • HW on classification out today • Due 4/23 • Can work in pairs

  3. Reinforcement Learning • Basic idea: • Receive feedback in the form of rewards • Agent’s utility is defined by the reward function • Must learn to act so as to maximize expected utility • Change the rewards, change the behavior • Examples: • Playing a game, reward at the end for winning / losing • Vacuuming a house, reward for each piece of dirt picked up • Automated taxi, reward for each passenger delivered

  4. Maximum Expected Utility • MEU: An agent should chose the action which maximizes its expected utility, given its knowledge • General principle for decision making • Often taken as the definition of rationality • Let’s decompress this definition…

  5. Reminder: Expectations • Often a quantity of interest depends on a random variable • The expected value of a function is the average output, weighted by some distribution over inputs • Example: How late will I be? • Lateness is a function of traffic: L(T=none) = -10, L(T=light) = -5, L(T=heavy) = 15 • What is my expected lateness? • Need to specify some belief over T to weight the outcomes • Say P(T) = {none: 2/5, light: 2/5, heavy: 1/5} • The expected lateness:

  6. Expectations • Real valued functions of random variables: • Expectation of a function a random variable • Example: Expected value of a fair die roll

  7. Utilities • Utilities are functions from outcomes (states of the world) to real numbers that describe an agent’s preferences • Where do utilities come from? • In a game, may be simple (+1/-1) • Utilities summarize the agent’s goals • Theorem: any set of preferences between outcomes can be summarized as a utility function (provided the preferences meet certain conditions) • In general, we utilities are determined from rewards and actions emerge to maximize expected utility.

  8. Preferences • An agent chooses among: • Prizes: A, B, etc. • Lotteries: situations with uncertain prizes • Notation:

  9. Rational Preferences • We want some constraints on preferences before we call them rational • For example: an agent with intransitive preferences can be induced to give away all its money • If B > C, then an agent with C would pay (say) 1 cent to get B • If A > B, then an agent with B would pay (say) 1 cent to get A • If C > A, then an agent with A would pay (say) 1 cent to get C

  10. Rational Preferences • Preferences of a rational agent must obey constraints. • These constraints (plus one more) are the axioms of rationality • Theorem: Rational preferences imply behavior describable as maximization of expected utility

  11. MEU Principle • Theorem: • [Ramsey, 1931; von Neumann & Morgenstern, 1944] • Given any preferences satisfying these constraints, there exists a real-valued function U such that: • Maximum expected likelihood (MEU) principle: • Choose the action that maximizes expected utility • Note: an agent can be entirely rational (consistent with MEU) without ever representing or manipulating utilities and probabilities • E.g., a lookup table for perfect tictactoe, reflex vacuum cleaner

  12. Human Utilities • Utilities map states to real numbers. Which numbers? • Standard approach to assessment of human utilities: • Compare a state A to a standard lottery Lp between • ``best possible prize'' u+ with probability p • ``worst possible catastrophe'' u- with probability 1-p • Adjust lottery probability p until A ~ Lp • Resulting p is a utility in [0,1]

  13. Utility Scales • Normalized utilities: u+ = 1.0, u- = 0.0 • Micromorts: one-millionth chance of death, useful for paying to reduce product risks, etc. • QALYs: quality-adjusted life years, useful for medical decisions involving substantial risk • One year with good health = 1 QALY • Note: behavior is invariant under positive linear transformation • With deterministic prizes only (no lottery choices), only ordinal utility can be determined, i.e., total order on prizes

  14. Example: Insurance • Consider the lottery [0.5,$1000; 0.5,$0] • What is its expected monetary value? ($500) • What is its certainty equivalent? • Monetary value acceptable in lieu of lottery • $400 for most people • Difference of $100 is the insurance premium • There’s an insurance industry because people will pay to reduce their risk • If everyone were risk-prone, no insurance needed!

  15. Money • Money does not behave as a utility function • Given a lottery L: • Define expected monetary value EMV(L) • Usually U(L) < U(EMV(L)) • I.e., people are risk-averse • Utility curve: for what probability p am I indifferent between: • A prize x • A lottery [p,$M; (1-p),$0] for large M? • Typical empirical data, extrapolated with risk-prone behavior:

  16. Example: Human Rationality? • Famous example of Allais (1953) • A: [0.8,$4k; 0.2,$0] • B: [1.0,$3k; 0.0,$0] • C: [0.2,$4k; 0.8,$0] • D: [0.25,$3k; 0.75,$0] • Most people prefer B > A, C > D • But if U($0) = 0, then • B > A  U($3k) > 0.8 U($4k) • C > D  0.8 U($4k) > U($3k)

  17. Reinforcement Learning DEMO • Basic idea: • Receive feedback in the form of rewards • Agent’s utility is defined by the reward function • Must learn to act so as to maximize expected utility • Change the rewards, change the behavior • Examples: • Learning your way around, reward for reaching the destination. • Playing a game, reward at the end for winning / losing • Vacuuming a house, reward for each piece of dirt picked up • Automated taxi, reward for each passenger delivered

  18. Markov Decision Processes • Markov decision processes (MDPs) • A set of states s  S • A model T(s,a,s’) = P(s’ | s,a) • Probability that action a in state s leads to s’ • A reward function R(s, a, s’) (sometimes just R(s) for leaving a state or R(s’) for entering one) • A start state (or distribution) • Maybe a terminal state • MDPs are the simplest case of reinforcement learning • In general reinforcement learning, we don’t know the model or the reward function

  19. Example: High-Low • Three card types: 2, 3, 4 • Infinite deck, twice as many 2’s • Start with 3 showing • After each card, you say “high” or “low” • New card is flipped • If you’re right, you win the points shown on the new card • Ties are no-ops • If you’re wrong, game ends 3 4 2 2

  20. High-Low • States: 2, 3, 4, done • Actions: High, Low • Model: T(s, a, s’): • P(s’=done | 4, High) = 3/4 • P(s’=2 | 4, High) = 0 • P(s’=3 | 4, High) = 0 • P(s’=4 | 4, High) = 1/4 • P(s’=done | 4, Low) = 0 • P(s’=2 | 4, Low) = 1/2 • P(s’=3 | 4, Low) = 1/4 • P(s’=4 | 4, Low) = 1/4 • … • Rewards: R(s, a, s’): • Number shown on s’ if s  s’ • 0 otherwise • Start: 3 4 Note: could choose actions with search. How?

  21. State Reward Action Elements of RL • Transition model, how action influences states • Reward R, immediate value of state-action transition • Policy , maps states to actions Agent Policy Environment

  22. MDP Solutions • In deterministic single-agent search, want an optimal sequence of actions from start to a goal • In an MDP, like expectimax, want an optimal policy (s) • A policy gives an action for each state • Optimal policy maximizes expected utility (i.e. expected rewards) if followed • Defines a reflex agent Optimal policy when R(s, a, s’) = -0.04 for all non-terminals s

  23. Example Optimal Policies R(s) = -0.01 R(s) = -0.03 R(s) = -0.4 R(s) = -2.0

  24. Finding Optimal Policies Demo

  25. Stationarity • In order to formalize optimality of a policy, need to understand utilities of reward sequences • Typically consider stationary preferences: • Theorem: only two ways to define stationary utilities • Additive utility: • Discounted utility:

  26. Infinite Utilities?! • Problem: infinite state sequences with infinite rewards • Solutions: • Finite horizon: • Terminate after a fixed T steps • Gives nonstationary policy ( depends on time left) • Absorbing state(s): guarantee that for every policy, agent will eventually “die” (like “done” for High-Low) • Discounting: for 0 <  < 1 • Smaller  means smaller horizon

  27. How (Not) to Solve an MDP • The inefficient way: • Enumerate policies • For each one, calculate the expected utility (discounted rewards) from the start state • E.g. by simulating a bunch of runs • Choose the best policy • We’ll return to a (better) idea like this later

  28. Utility of a State • Define the utility of a state under a policy: V(s) = expected total (discounted) rewards starting in s and following  • Recursive definition (one-step look-ahead):

  29. Policy Evaluation • Idea one: turn recursive equations into updates • Idea two: it’s just a linear system, solve with Matlab (or Mosek, or Cplex)

  30. Example: High-Low • Policy: always say “high” • Iterative updates:

  31. Optimal Utilities • Goal: calculate the optimal utility of each state V*(s) = expected (discounted) rewards with optimal actions • Why: Given optimal utilities, MEU tells us the optimal policy

  32. That’s my equation! Bellman’s Equation for Selecting actions • Definition of utility leads to a simple relationship amongst optimal utility values: Optimal rewards = maximize over first action and then follow optimal policy Formally: Bellman’s Equation

  33. Example: GridWorld

  34. Value Iteration • Idea: • Start with bad guesses at all utility values (e.g. V0(s) = 0) • Update all values simultaneously using the Bellman equation (called a value update or Bellman update): • Repeat until convergence • Theorem: will converge to unique optimal values • Basic idea: bad guesses get refined towards optimal values • Policy may converge long before values do

  35. Example: Bellman Updates

  36. Example: Value Iteration • Information propagates outward from terminal states and eventually all states have correct value estimates [DEMO]

  37. Convergence* • Define the max-norm: • Theorem: For any two approximations U and V • I.e. any distinct approximations must get closer to each other, so, in particular, any approximation must get closer to the true U and value iteration converges to a unique, stable, optimal solution • Theorem: • I.e. one the change in our approximation is small, it must also be close to correct

  38. Policy Iteration • Alternate approach: • Policy evaluation: calculate utilities for a fixed policy until convergence (remember the beginning of lecture) • Policy improvement: update policy based on resulting converged utilities • Repeat until policy converges • This is policy iteration • Can converge faster under some conditions

More Related