Exactly Learning Automata of Small Cover Time

We present algorithms for exactly learning unknown environments that can be described by deterministic finite automata. The learner performs a walk on the target automaton, where at each step it observes the output of the state it is at, and chooses a labeled edge to traverse to the next state. The learner has no means of a reset, and does not have access to a teacher that answers equivalence queries and gives the learner counterexamples to its hypotheses. We present two algorithms: The first is for the case in which the outputs observed by the learner are always correct, and the second is for the case in which the outputs might be corrupted by random noise. The running times of both algorithms are polynomial in the cover time of the underlying graph of the target automaton.

[1]  Kenneth Basye,et al.  Inferring Finite Automata with Stochastic Output Functions and an Application to Map Learning , 2004, Machine Learning.

[2]  Yasubumi Sakakibara,et al.  On Learning from Queries and Counterexamples in the Presence of Noise , 1991, Inf. Process. Lett..

[3]  Ronitt Rubinfeld,et al.  Efficient algorithms for learning to play repeated games against computationally bounded adversaries , 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

[4]  Lance Fortnow,et al.  Optimality and domination in repeated games with bounded players , 1993, STOC '94.

[5]  Ronald L. Rivest,et al.  Diversity-based inference of finite automata , 1994, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[6]  Dana Angluin,et al.  A Note on the Number of Queries Needed to Identify Regular Languages , 1981, Inf. Control..

[7]  Tao Jiang,et al.  Learning regular languages from counterexamples , 1988, COLT '88.

[8]  Dana Angluin.  Negative results for equivalence queries , 1990, Mach. Learn..

[9]  Russ Bubley,et al.  Randomized algorithms , 1995, CSUR.

[10]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[11]  Mark Jerrum,et al.  Approximate Counting, Uniform Generation and Rapidly Mixing Markov Chains , 1987, WG.

[12]  Francesco Bergadano,et al.  Learning Behaviors of Automata from Multiplicity and Equivalence Queries , 1994, SIAM J. Comput..

[13]  Ronitt Rubinfeld,et al.  Efficient learning of typical finite automata from random walks , 1993, STOC.

[14]  Umesh V. Vazirani,et al.  On the learnability of finite automata , 1988, Annual Conference Computational Learning Theory.

[15]  Ronald L. Rivest,et al.  Inference of finite automata using homing sequences , 1989, STOC '89.

[16]  Dana Angluin,et al.  Learning Regular Sets from Queries and Counterexamples , 1987, Inf. Comput..

[17]  Itzhak Gilboa,et al.  Bounded Versus Unbounded Rationality: The Tyranny of the Weak , 1989 .

[18]  Ronitt Rubinfeld,et al.  Learning fallible finite state automata , 1993, COLT '93.

[19]  Richard J. Lipton,et al.  Random walks, universal traversal sequences, and the complexity of maze problems , 1979, 20th Annual Symposium on Foundations of Computer Science (sfcs 1979).

[20]  Michael Frazier,et al.  Learning from a consistently ignorant teacher , 1994, COLT '94.

[21]  Ronitt Rubinfeld,et al.  On learning bounded-width branching programs , 1995, COLT '95.

[22]  Dana Angluin,et al.  Learning from noisy examples , 1988, Machine Learning.

[23]  Carl H. Smith,et al.  Inductive Inference: Theory and Methods , 1983, CSUR.

[24]  Leslie G. Valiant,et al.  Cryptographic Limitations on Learning Boolean Formulae and Finite Automata , 1993, Machine Learning: From Theory to Applications.

[25]  Michael A. Bender,et al.  The power of team exploration: two robots can learn unlabeled directed graphs , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.