Reinforcement Learning Methods (RLMs) typically select candidate solutions stochastically based on a credibility space of hypotheses which the RLM maintains, either implicitly or explicitly. RLMs typically have both inductive and deductive aspects: they inductively improve their credibility space on a stage-by stage basis; they deductively select an appropriate response to incoming stimuli usin...

In this paper, we describe FACS, a new Michigan style architecture able to build Finite-State Automata controllers for agents learning to solve nonMarkov problems. FACS relies on a population of partial automata and implements a Reinforcement Learning algorithm to compute the strength of each automaton and a Genetic Algorithm to select and discover efficient automata. We detail our approach and...

Optimized task scheduling is one of the most important challenges in multiprocessor environments such as parallel and distributed systems. In such these systems, each parallel program is decomposed into the smaller segments so-called tasks. Task execution times, precedence constrains and communication costs are modeled by using a directed acyclic graph (DAG) named task graph. The goal is to min...

Automata learning has been successfully applied in the verification of hardware and software. The size of the automaton model learned is a bottleneck for scalability and hence optimizations that enable learning of compact representations are important. In this paper we develop a class of optimizations and an accompanying correctness proof for learning algorithms, building upon a general framewo...

Although considerable interest has been shown in language inference and automata induction using recurrent neural networks, success of these models has mostly been limited to regular languages. We have previously demonstrated that Neural Network Pushdown Automaton (NNPDA) model is capable of learning deterministic context-free languages (e.g., anbn and parenthesis languages) from examples. Howe...

In this paper, we first define the notion of a complete general fuzzyautomaton with threshold c and construct an $H_{nu}$- group, as well as commutativehypergroups, on the set of states of a complete general fuzzy automatonwith threshold c. We then define invertible general fuzzy automata, discussthe notions of “homogeneity, “separation, “thresholdness connected, “thresholdnessinner irreducible...

Although considerable interest has been shown in language inference and automata induction using recurrent neural networks, success of these models has mostly been limited to regular languages. We have previously demonstrated that Neural Network Pushdown Automaton (NNPDA) model is capable of learning deterministic context-free languages (e.g., a n b n and parenthesis languages) from examples. H...

This paper discusses a load balancing heuristic in a general-purpose distributed computer system. We implemented a task scheduler based on the concept of a Stochastic Learning Automaton on a network of Unix workstations. The used heuristic and our implementation are shortly described. Creating an executable artiicial workload, a number of experiments examined diierent learning schemes. Using a ...

Automata learning is a technique that has successfully been applied in verification, with the automaton type varying depending on the application domain. Adaptations of automata learning algorithms for increasingly complex types of automata have to be developed from scratch because there was no abstract theory offering guidelines. This makes it hard to devise such algorithms, and it obscures th...