Learning to Play Chess Using Temporal Differences

In this paper we present TDLEAF(), a variation on the TD() algorithm that enables it to be used in conjunction with game-tree search. We present some experiments in which our chess program KnightCap used TDLEAF() to learn its evaluation function while playing on Internet chess servers. The main success we report is that KnightCap improved from a 1650 rating to a 2150 rating in just 308 games and 3 days of play. As a reference, a rating of 1650 corresponds to about level B human play (on a scale from E (1000) to A (1800)), while 2150 is human master level. We discuss some of the reasons for this success, principle among them being the use of on-line, rather than self-play. We also investigate whether TDLEAF() can yield better results in the domain of backgammon, where TD() has previously yielded striking success.     

Least Squares Policy Evaluation Algorithms with Linear Function Approximation

We consider policy evaluation algorithms within the context of infinite-horizon dynamic programming problems with discounted cost. We focus on discrete-time dynamic systems with a large number of states, and we discuss two methods, which use simulation, temporal differences, and linear cost function approximation. The first method is a new gradient-like algorithm involving least-squares subproblems and a diminishing stepsize, which is based on the -policy iteration method of Bertsekas and Ioffe. The second method is the LSTD() algorithm recently proposed by Boyan, which for =0 coincides with the linear least-squares temporal-difference algorithm of Bradtke and Barto. At present, there is only a convergence result by Bradtke and Barto for the LSTD(0) algorithm. Here, we strengthen this result by showing the convergence of LSTD(), with probability 1, for every [0, 1].     

The π-Calculus in Direct Style

We introduce a calculus which is a direct extension of both the and the calculi. We give a simple type system for it, that encompasses both Curry's type inference for the -calculus, and Milner's sorting for the -calculus as particular cases of typing. We observe that the various continuation passing style transformations for -terms, written in our calculus, actually correspond to encodings already given by Milner and others for evaluation strategies of -terms into the -calculus. Furthermore, the associated sortings correspond to well-known double negation translations on types. Finally we provide an adequate CPS transform from our calculus to the -calculus. This shows that the latter may be regarded as an assembly language, while our calculus seems to provide a better programming notation for higher-order concurrency. We conclude by discussing some alternative design decisions.     

A Full Bayesian Approach to Curve and Surface Reconstruction

When interpolating incomplete data, one can choose a parametric model, or opt for a more general approach and use a non-parametric model which allows a very large class of interpolants. A popular non-parametric model for interpolating various types of data is based on regularization, which looks for an interpolant that is both close to the data and also smooth in some sense. Formally, this interpolant is obtained by minimizing an error functional which is the weighted sum of a fidelity term and a smoothness term.The classical approach to regularization is: select optimal weights (also called hyperparameters) that should be assigned to these two terms, and minimize the resulting error functional.However, using only the optimal weights does not guarantee that the chosen function will be optimal in some sense, such as the maximum likelihood criterion, or the minimal square error criterion. For that, we have to consider all possible weights.The approach suggested here is to use the full probability distribution on the space of admissible functions, as opposed to the probability induced by using a single combination of weights. The reason is as follows: the weight actually determines the probability space in which we are working. For a given weight , the probability of a function f is proportional to exp(– f² _uu du) (for the case of a function with one variable). For each different , there is a different solution to the restoration problem; denote it by f. Now, if we had known , it would not be necessary to use all the weights; however, all we are given are some noisy measurements of f, and we do not know the correct . Therefore, the mathematically correct solution is to calculate, for every , the probability that f was sampled from a space whose probability is determined by , and average the different f's weighted by these probabilities. The same argument holds for the noise variance, which is also unknown.Three basic problems are addressed is this work: Computing the MAP estimate, that is, the function f maximizing Pr(f/D) when the data D is given. This problem is reduced to a one-dimensional optimization problem. Computing the MSE estimate. This function is defined at each point x as f(x)Pr(f/D) f. This problem is reduced to computing a one-dimensional integral.In the general setting, the MAP estimate is not equal to the MSE estimate. Computing the pointwise uncertainty associated with the MSE solution. This problem is reduced to computing three one-dimensional integrals.     

Fast Online Q(λ)

Q()-learning uses TD()-methods to accelerate Q-learning. The update complexity of previous online Q() implementations based on lookup tables is bounded by the size of the state/action space. Our faster algorithm's update complexity is bounded by the number of actions. The method is based on the observation that Q-value updates may be postponed until they are needed.     

The Postal Network: A Recursive Network for Parameterized Communication Model

The postal network is an interconnection network that possesses many desirable properties in networking applications. It includes hypercubes and Fibonacci cubes as its special cases. Basically, the postal network forms a series (with series number ) that is based on the sequence N (n)=N (n–1)+N (n–), where n is the dimension and N (n) represents the number of nodes in an n-dimensional postal network in series . In this paper, we study topological properties of postal networks and relationships between different postal networks. One application of postal networks is also shown in implementing barrier synchronization using a special spanning tree called a postal tree. The postal network can also be considered as a flexible version of the hypercube by relaxing the restriction on the number of nodes, and hence, makes it possible to construct multicomputers with arbitrary sizes.     

A geometric view of parametric linear programming

We present a new definition of optimality intervals for the parametric right-hand side linear programming (parametric RHS LP) Problem () = min{c ^t x¦Ax =b + ¯b,x 0}. We then show that an optimality interval consists either of a breakpoint or the open interval between two consecutive breakpoints of the continuous piecewise linear convex function (). As a consequence, the optimality intervals form a partition of the closed interval {; ¦()¦ < }. Based on these optimality intervals, we also introduce an algorithm for solving the parametric RHS LP problem which requires an LP solver as a subroutine. If a polynomial-time LP solver is used to implement this subroutine, we obtain a substantial improvement on the complexity of those parametric RHS LP instances which exhibit degeneracy. When the number of breakpoints of () is polynomial in terms of the size of the parametric problem, we show that the latter can be solved in polynomial time.This research was partially funded by the United States Navy-Office of Naval Research under Contract N00014-87-K-0202. Its financial support is gratefully acknowledged.     

Higher-Order and Modal Logic as a Framework for Explanation-Based Generalization

Certain tasks, such as formal program development and theorem proving, fundamentally rely upon the manipulation of higher-order objects such as functions and predicates. Computing tools intended to assist in performing these tasks are at present inadequate in both the amount of knowledge they contain (i.e., the level of support they provide) and in their ability to learn (i.e., their capacity to enhance that support over time). The application of a relevant machine learning technique—explanation-based generalization (EBG)—has thus far been limited to first-order problem representations. We extend EBG to generalize higher-order values, thereby enabling its application to higher-order problem encodings.Logic programming provides a uniform framework in which all aspects of explanation-based generalization and learning may be defined and carried out. First-order Horn logics (e.g., Prolog) are not, however, well suited to higher-order applications. Instead, we employ Prolog, a higher-order logic programming language, as our basic framework for realizing higher-order EBG. In order to capture the distinction between domain theory and training instance upon which EBG relies, we extend Prolog with the necessity operator of modal logic. We develop a meta-interpreter realizing EBG for the extended language, Prolog, and provide examples of higher-order EBG.     

Designing broadcasting algorithms in the postal model for message-passing systems

In many distributed-memory parallel computers and high-speed communication networks, the exact structure of the underlying communication network may be ignored. These systems assume that the network creates a complete communication graph between the processors, in which passing messages is associated with communication latencies. In this paper we explore the impact of communication latencies on the design of broadcasting algorithms for fully connected message-passing systems. For this purpose, we introduce thepostal model that incorporates a communication latency parameter 1. This parameter measures the inverse of the ratio between the time it takes an originator of a message to send the message and the time that passes until the recipient of the message receives it. We present an optimal algorithm for broadcasting one message in systems withn processors and communication latency , the running time of which is (( logn)/log( + 1)). For broadcastingm 1 messages, we first examine several generalizations of the algorithm for broadcasting one message and then analyze a family of broadcasting algorithms based on degree-d trees. All the algorithms described in this paper are practical event-driven algorithms that preserve the order of messages.     

Context-free text grammars

A text is a triple=(, ₁, ₂) such that is a labeling function, and ₁ and ₂ are linear orders on the domain of ; hence may be seen as a word (, ₁) together with an additional linear order ₂ on the domain of . The order ₂ is used to give to the word (, ₁) itsindividual hierarchical representation (syntactic structure) which may be a tree but it may be also more general than a tree. In this paper we introducecontext-free grammars for texts and investigate their basic properties. Since each text has its own individual structure, the role of such a grammar should be that of a definition of a pattern common to all individual texts. This leads to the notion of ashapely context-free text grammar also investigated in this paper.     

Technical Update: Least-Squares Temporal Difference Learning

TD./ is a popular family of algorithms for approximate policy evaluation in large MDPs. TD./ works by incrementally updating the value function after each observed transition. It has two major drawbacks: it may make inefficient use of data, and it requires the user to manually tune a stepsize schedule for good performance. For the case of linear value function approximations and = 0, the Least-Squares TD (LSTD) algorithm of Bradtke and Barto (1996, Machine learning, 22:1–3, 33–57) eliminates all stepsize parameters and improves data efficiency.This paper updates Bradtke and Barto's work in three significant ways. First, it presents a simpler derivation of the LSTD algorithm. Second, it generalizes from = 0 to arbitrary values of ; at the extreme of = 1, the resulting new algorithm is shown to be a practical, incremental formulation of supervised linear regression. Third, it presents a novel and intuitive interpretation of LSTD as a model-based reinforcement learning technique.     

Average-Case Competitive Analyses for Ski-Rental Problems

Let s be the ratio of the cost for purchasing skis over the cost for renting them. Then the famous result for the ski-rental problem shows that skiers should buy their skis after renting them (s - 1) times, which gives us an optimal competitive ratio of 2 - 1/s. In practice, however, it appears that many skiers buy their skis before this optimal point of time and also many skiers keep renting them forever. In this paper we show that this behavior of skiers is quite reasonable by using an average-case competitive ratio. For an exponential input distribution f(t) = e^-t, optimal strategies are (i) if 1/ \leq s, then skiers should rent their skis forever and (ii) otherwise they should purchase them after renting approximately s² (相似文献   

Reduction and unification in lambda calculi with a general notion of subtype

Reduction, equality, and unification are studied for a family of simply typed -calculi with subtypes. The subtype relation is required to relate base types only to base types and to satisfy some order-theoretic conditions. Constants are required to have a least type, that is, no overloading. We define the usual and a subtype-dependent -reduction. These are related to a typed equality relation and shown to be confluent in a certain sense. We present a generic algorithm for preunification modulo -conversion and an arbitrary subtype relation. Furthermore it is shown that unification with respect to any subtype relation is universal.     

The Theory of Fexprs is Trivial

We provide a very simple model of a reflective facility based onthe pure -calculus, and we show that its theory of contextual equivalenceis trivial: two terms in the language are contextually equivalent iff theyare -congruent.     

Constructing sets of functions which have a givenF-cardinality

The termF-cardinality of (=F-card()) is introduced whereF: ^{n n} is a partial function and is a set of partial functionsf: ^{n n} . TheF-cardinality yields a lower bound for the worst-case complexity of computingF if only functionsf can be evaluated by the underlying abstract automaton without conditional jumps. This complexity bound isindependent from the oracles available for the abstract machine. Thus it is shown that any automaton which can only apply the four basic arithmetic operations needs (n logn) worst-case time to sortn numbers; this result is even true if conditional jumps witharbitrary conditions are possible. The main result of this paper is the following: Given a total functionF: ^{n n} and a natural numberk, it is almost always possible to construct a set such that itsF-cardinality has the valuek; in addition, can be required to be closed under composition of functionsf,g . Moreover, ifF is continuous, then consists of continuous functions.     

Conditions for the Light-Traffic Insensitivity to Loss Probability in a GI/G/m/0 Queueing System

A loss queueing system GI/G/m/0 is considered. Let a(x) be a p.d.f. of interarrival intervals. Assume that this function behaves like cx^-1 for small x. Further let B(x) be a d.f. of service time; (1/) be the mean service time. Conditions are derived for the light-traffic insensitivity of the loss probability to the form of B(x) as (/ ) 0. In particular, the condition = 1 is necessary. Estimates for the loss probability are obtained.     

Simultaneous inner and outer approximation of shapes

For compact Euclidean bodiesP, Q, we define (P, Q) to be the smallest ratior/s wherer > 0,s > 0 satisfy . HeresQ denotes a scaling ofQ by the factors, andQ,Q are some translates ofQ. This function gives us a new distance function between bodies which, unlike previously studied measures, is invariant under affine transformations. If homothetic bodies are identified, the logarithm of this function is a metric. (Two bodies arehomothetic if one can be obtained from the other by scaling and translation.)For integerk 3, define (k) to be the minimum value such that for each convex polygonP there exists a convexk-gonQ with (P, Q) (k). Among other results, we prove that 2.118 ... <-(3) 2.25 and (k) = 1 + (k ^–2). We give anO(n ² log² n)-time algorithm which, for any input convexn-gonP, finds a triangleT that minimizes (T, P) among triangles. However, in linear time we can find a trianglet with (t, P)<-2.25.Our study is motivated by the attempt to reduce the complexity of the polygon containment problem, and also the motion-planning problem. In each case we describe algorithms which run faster when certain implicitslackness parameters of the input are bounded away from 1. These algorithms illustrate a new algorithmic paradigm in computational geometry for coping with complexity.Work of all authors was partially supported by the ESPRIT II Basic Research Actions Program of the EC under Contract No. 3075 (project ALCOM). Rudolf Fleischer and Kurt Mehlhorn acknowledge also DFG (Grant SPP Me 620/6). Chee Yap acknowledges also DFG (Grant Be 142/46-1) and NSF (Grants DCR-84-01898 and CCR-87-03458). This research was performed when Günter Rote and Chee Yap were at the Freie Universität Berlin.     

A CUCH-machine: The automatic treatment of bound variables

This paper describes a machine for reducing a -formula (explicitly given or implicitly by a system of recursive equations) to principal --normal form, with particular attention to the memory structures needed for the purpose, and with some important features: (1) any kind of collision is permitted; (2) the processing of subformulas which will be thrown away [e.g., ((xy)x) in ((yz)(xy)x)] is avoided; (3) there is no need to introduce any fixed point operator like , etc. The machine structure entails: (1) some store to memorize as side-effects assignment statements with the r.h.s. of a given shape. (2) a number of stacks, one for every in the initial formula, partitioned naturally in classes (chains). These stacks admit as entries only words representing variables and they are peculiar in that the operations admitted on the top arewriting anderasing and the operations admitted on the pseudo-top arereading,read-protecting, andresetting readability (the last two operations are chain operations). This structure is critically motivated. (3) A workstack. (4) A pointerstack. The computation runs through four phases: -generation, -run, -generation, -run. Every generation- (run-) phase is rather recognition- (transformation-) oriented, but we found it more stimulating to emphasize technical similarities rather than methodological differences. Every phase is described and four examples are extensively developed.     

CPS Translations and Applications: The Cube and Beyond

Continuation passing style (CPS) translations of typed -calculi have numerous applications. However, the range of these applications has been confined by the fact that CPS translations are known for non-dependent type systems only, thus excluding well-known systems like the calculus of constructions (CC) and the logical frameworks (LF). This paper presents techniques for CPS translating systems with dependent types, with an emphasis on pure type-theoretical applications.In the first part of the paper we review several lines of work in which the need for CPS translations of dependent type systems has arisen, and discuss the difficulties involved with CPS translating such systems. One way of overcoming these difficulties is to work with so-called domain-free type systems. Thus, instead of Barendregt's -cube we shall consider the domain-free -cube, and instead of traditional pure type systems, we shall consider domain-free pure type systems.We therefore begin the second part by reviewing the domain-free -cube, which includes domain-free versions of CC and LF, and then present CPS translations for all the systems of the domain-free -cube. We also introduce Direct Style (DS) (i.e., inverse CPS) translations for all the systems of the domain-free -cube; such DS translations, which have been used in a number of applications, were previously formulated for untyped and simply-typed languages only.In the third part we review domain-free pure type systems and generalize the CPS translations of the domain-free -cube to a large class of domain-free pure type systems which includes most of the systems that appear in the literature, including those of the domain-free -cube. Many translations that appear in the literature arise as special cases of ours.In the fourth part of the paper we present two approaches to CPS translations of traditional pure type systems. The first, indirect, technique lifts the CPS translation of domain-free pure type systems to the analogous class of traditional pure type systems by using results that relate derivations in domain-free and traditional pure type systems. The second, direct, approach translates derivations, requiring a certain order on derivations to be well-founded. Both techniques yield translations for most of the systems that appear in the literature, including those of Barendregt's -cube.     

Defaults as restrictions on classical Hilbert-style proofs

Since the earliest formalisation of default logic by Reiter many contributions to this appealing approach to nonmonotonic reasoning have been given. The different formalisations are here presented in a general framework that gathers the basic notions, concepts and constructions underlying default logic. Our view is to interpret defaults as special rules that impose a restriction on the juxtaposition of monotonic Hubert-style proofs of a given logicL. We propose to describe default logic as a logic where the juxtaposition of default proofs is subordinate to a restriction condition . Hence a default logic is a pair (L, ) where properties of the logic , like compactness, can be interpreted through the restriction condition . Different default systems are then given a common characterization through a specific condition on the logicL. We also prove cumulativity for any default logic (L, ) by slightly modifying the notion of default proof. We extend, in fact, the language ofL in a way close to that followed by Brewka in the formulation of his cumulative default system. Finally we show the existence of infinitely many intermediary default logics, depending on and called linear logics, which lie between Reiter's and ukaszewicz' versions of default logic.Work carried out in the framework of the agreement between Italian PT Administration and FUBLaforia, Université Paris VI Pierre et Marie Curie, 4 Place Jussieu,Tour 46, 75252 Paris, France