1 / 29

Decision Making in Intelligent Systems Lecture 3

Decision Making in Intelligent Systems Lecture 3. BSc course Kunstmatige Intelligentie 2008 Bram Bakker Intelligent Systems Lab Amsterdam Informatics Institute Universiteit van Amsterdam bram@science.uva.nl. Overview of this lecture. Solving the full RL problem

krisalyn
Download Presentation

Decision Making in Intelligent Systems Lecture 3

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. Decision Making in Intelligent SystemsLecture 3 BSc course Kunstmatige Intelligentie 2008 Bram Bakker Intelligent Systems Lab Amsterdam Informatics Institute Universiteit van Amsterdam bram@science.uva.nl

  2. Overview of this lecture • Solving the full RL problem • Given that we have the MDP model • Dynamic Programming • Policy iteration • Value iteration

  3. r r r . . . . . . t +1 t +2 s s t +3 s s t +1 t +2 t +3 a a a a t t +1 t +2 t t +3 Markov Decision Processes

  4. Returns: A Unified Notation • In episodic tasks, we number the time steps of each episode starting from zero. • Think of each episode as ending in an absorbing state that always produces reward of zero: • We can cover all cases by writing

  5. Value Functions • The value of a state is the expected return starting from that state; depends on the agent’s policy: • The value of taking an action in a stateunder policy p is the expected return starting from that state, taking that action, and thereafter following p :

  6. Bellman Equation for a Policy p The basic idea: So: Or, without the expectation operator:

  7. Bellman Optimality Equation for V* The value of a state under an optimal policy must equal the expected return for the best action from that state: is the unique solution of this system of nonlinear equations.

  8. Dynamic Programming (DP) • A collection of classical solution methods for MDPs • Policy iteration • Value iteration • DP can be used to compute value functions, and hence, optimal policies • Assumes a known MDP model (state transition model and reward model) • Combination of Policy Evaluation and Policy Improvement

  9. Policy Evaluation: for a given policy p, compute the state-value function Policy Evaluation Recall:

  10. Iterative Methods a “sweep” A sweep consists of applying a backup operation to each state, And results in a new value function for iteration k+1. A full policy-evaluation backup:

  11. Bootstrapping A full policy-evaluation backup: The new estimated value for each state s is based on the estimated old value of all possible successor states s’ Bootstrapping: estimating values based on your own estimates of values

  12. Iterative Policy Evaluation

  13. A Small Gridworld • An undiscounted episodic task • Nonterminal states: 1, 2, . . ., 14; • Terminal states shown as shaded squares • Actions that would take agent off the grid leave state unchanged • Reward is –1 until a terminal state is reached

  14. Iterative Policy Evaluationfor the Small Gridworld

  15. Suppose we have computed for a deterministic policy p. Policy Improvement

  16. Policy Improvement Continued

  17. Policy Iteration policy evaluation policy improvement “greedification”

  18. Policy Iteration

  19. Value Iteration Recall the full policy-evaluation backup: Here is the full value-iteration backup: Essentially, combines policy evaluation and improvement in one step

  20. Value Iteration Continued

  21. Iterative Policy Evaluationfor the Small Gridworld

  22. T T T T T T T T T T Dynamic Programming visualized T T T

  23. T T T T T T T T T T T T T T T T T T T T Monte Carlo

  24. Asynchronous DP • All the DP methods described so far require exhaustive sweeps of the entire state set. • Asynchronous DP does not use sweeps. Instead it works like this: • Repeat until convergence criterion is met: • Pick a state at random and apply the appropriate backup • Still need lots of computation, but does not get locked into hopelessly long sweeps • Can you select states to backup intelligently? YES: an agent’s experience can act as a guide.

  25. Generalized Policy Iteration Generalized Policy Iteration (GPI): any interaction of policy evaluation and policy improvement, independent of their granularity. A geometric metaphor for convergence of GPI:

  26. Efficiency of DP • To find an optimal policy is polynomial in the number of states… • BUT, the number of states is often astronomical, e.g., often growing exponentially with the number of state variables (what Bellman called “the curse of dimensionality”). • In practice, classical DP can be applied to problems with a few millions of states. • Asynchronous DP can be applied to larger problems, and appropriate for parallel computation. • It is surprisingly easy to come up with MDPs for which DP methods are not practical.

  27. Summary • Policy evaluation: estimate value of current policy • Policy improvement: determine new current policy by being greedy w.r.t. current value function • Policy iteration: alternate the above two processes • Value iteration: combine the above two processes in 1 step • Bootstrapping: updating estimates based on your own estimates • Full backups (to be contrasted with sample backups) • Generalized Policy Iteration (GPI)

  28. Before we start… • Questions? Are some concepts still unclear? • Are you making progress in the Prakticum? • Advice: I do not cover everything from the book in detail. Issues and algorithms that I emphasize in the lectures are the most important (also for exams).

  29. Next Class • Lecture next Monday: • Chapters 5 (& 6?) of Sutton & Barto

More Related