1 / 31

Nesterov’s excessive gap technique and poker

Nesterov’s excessive gap technique and poker. Andrew Gilpin CMU Theory Lunch Feb 28, 2007 Joint work with: Samid Hoda, Javier Peña, Troels Sørensen, Tuomas Sandholm. Outline. Two-person zero-sum sequential games First-order methods for convex optimization

luna
Télécharger la présentation

Nesterov’s excessive gap technique and poker

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. Nesterov’s excessive gap technique and poker Andrew Gilpin CMU Theory Lunch Feb 28, 2007 Joint work with: Samid Hoda, Javier Peña, Troels Sørensen, Tuomas Sandholm

  2. Outline • Two-person zero-sum sequential games • First-order methods for convex optimization • Nesterov’s excessive gap technique (EGT) • EGT for sequential games • Heuristics for EGT • Application to Texas Hold’em poker

  3. We want to solve: If Q1 and Q2 are simplices, this is the Nash equilibrium problem for two-person zero-sum matrix games If Q1 and Q2 are complexes, this is the Nash equilibrium problem for two-person zero-sum sequential games

  4. What’s a complex? It’s just like a simplex, but more complex. Each player’s complex encodes her set of realization plans in the game In particular, player 1’s complex is where E and e depend on the game…

  5. A B C D E F G H

  6. Recall our problem: where Q1 and Q2 are complexes Since Q1 and Q2 have a linear description, this problem can be solved as an LP. However, current LP solution methods do not scale

  7. (Un)scalability of LP solvers • Rhode Island poker [Shi & Littman 01] • LP has 91 million rows and columns • Applying GameShrink automated abstraction algorithm yields an LP with only 1.2 million rows and columns, and 50 million non-zeros [G. & Sandholm, 06a] • Solution requires 25 GB RAM and over a week of CPU time • Texas Hold’em poker • ~1018 nodes in game tree • Lossy abstractions need to be performed • Limitations of current solver technology primary limitation to achieving expert-level strategies [G. & Sandholm 06b, 07a] • Instead of standard LP solvers, what about a first-order method?

  8. Convex optimization Suppose we want to solve Note that this formulation captures ALL convex optimization problems (can model feasible space using an indicator function) where f is convex. For general f, convergence requires O(1/ε2) iterations (e.g., for subgradient methods) For smooth, strongly convex f with Lipschitz- continuous gradient, can be done in O(1/ε½) iterations Analysis based on black-box oracle access model. Can we do better by looking inside the box?

  9. Strong convexity A function is strongly convex if there exists such that for all and all is the strong convexity parameter of d

  10. Recall our problem: where Q1 and Q2 are complexes Equivalently: where and

  11. , , Unfortunately, Φ and f are non-smooth Fortunately, they have a special structure Let d1,d2 be smooth and strongly convex on Q1,Q2 These are called prox-functions Now let μ > 0 and consider: These are well-defined smooth functions

  12. Excessive gap condition From weak duality, we have that f(y) ≤ Φ(x) The excessive gap condition requires that fμ(y) ≤ Φμ(x) (EGC) The algorithm maintains (EGC), and gradually decreases μ As μ decreases, the smoothed functions approach the non-smooth functions, and thus iterates satisfying (EGC) converge to optimal solutions

  13. Nesterov’s main theorem Theorem [Nesterov 05] There exists an algorithm such that after at most N iterations, the iterates have duality gap at most Furthermore, each iteration only requires solving three problems of the form and performing three matrix-vector product operations on A.

  14. Nice prox functions A prox function d for Q is nice if it is: • Strongly convex continuous everywhere in Q, and differentiable in the relative interior of Q • The min of d over Q is 0 • The following maps are easily computable:

  15. Nice simplex prox function 1: Entropy

  16. Nice simplex prox function 2: Euclidean sargmax can be computed in O(n log n) time

  17. From the simplex to the complex Theorem [Hoda, G., Peña 06] A nice prox function can be constructed for the complex via a recursive application of any nice prox function for the simplex

  18. Prox function example Let be any nice simplex prox function. The prox function for this matrix is:

  19. Solving

  20. (similar to b(i-vii))

  21. Heuristics [G., Hoda, Peña, Sandholm 07] • Heuristic 1: Aggressive μ reduction • The μ given in the previous algorithm is a conservative choice guaranteeing convergence • In practice, we can do much better by aggressively pushing μ, while checking that the excessive gap condition is satisfied • Heuristic 2: Balanced μ reduction • To prevent one μ from dominating the other, we also perform periodic adjustments to keep them within a small factor of one another

  22. Matrix-vector multiplication in poker[G., Hoda, Peña, Sandholm 07] • The main time and space bottleneck of the algorithm is the matrix-vector product on A • Instead of storing the entire matrix, we can represent it as a composition of Kronecker products • We can also effectively take advantage of parallelization in the matrix-vector product to achieve near-linear speedup

  23. Memory usage comparison

  24. Poker • Poker is a recognized challenge problem in AI because (among other reasons) • the other players’ cards are hidden; • bluffing and other deceptive strategies are needed in a good player; • there is uncertainty about future events. • Texas Hold’em: most popular variant of poker • Two-player game tree has ~1018 nodes

  25. Potential-aware automated abstraction[G., Sandholm, Sørensen 07] • Most prior automated abstraction algorithms employ a myopic expected value computation as a similarity metric • This ignores hands like flush draws where although the probability of winning is small, the payoff could be high • Our newest algorithm considers higher-dimensional spaces consisting of histograms over abstracted classes of states from later stages of the game • This enables our bottom-up abstraction algorithm to automatically take into account positive and negative potential

  26. Solving the four-round model • Computed abstraction with • 20 first-round buckets • 800 second-round buckets • 4800 third-round buckets • 28800 fourth-round buckets • Algorithm using 30 GB RAM • Simply representing as an LP requires 32 TB • Outputs new, improved solution every 2.5 days

  27. [G., Sandholm, Sørensen 07]

  28. [G., Sandholm, Sørensen 07]

  29. [G., Sandholm, Sørensen 07]

  30. Future research • Customizing second-order (e.g. interior-point methods) for the equilibrium problem • Additional heuristics for improving practical performance of EGT algorithm • Techniques for finding an optimal solution from an ε-solution

  31. Thank you ☺

More Related