This paper describes two complementary algorithms developed for mobile robots operating within unknown, maze-type environments. The first is an environmental mapping and navigation algorithm which ensures complete coverage of a maze with apriori unknown wall locations, and the second a stochastic learning automaton approach for general obstacle avoidance within the maze. The environmental mappi...

Push systems are not suitable for applications with a priori unknown, dynamic client demands. This paper proposes an adaptive push-based system. It suggests the use of a learning automaton at the broadcast server to provide adaptivity to an existing push system while maintaining its computational complexity. Using simple feedback from the clients, the automaton continuously adapts to the client...

Original scientific paper A Fuzzy Skinner Operant Conditioning Automaton (FSOCA) is constructed based on Operant Conditioning Mechanism with Fuzzy Set theory. The main character of FSOCA automaton is: the fuzzed results of state by Gaussian function are used as fuzzy state sets; the fuzzy mapping rules of fuzzyconditioning-operation replace the stochastic "conditioning-operant" mapping sets. So...

Abstract We show the decidability of finite sequentiality problem for unambiguous max-plus tree automata. A automaton is called if there at most one accepting run on every tree. The asks whether a given automaton, exist finitely many deterministic automata whose pointwise maximum equivalent to automaton.

Minimum vertex cover problem is an NP-Hard problem with the aim of finding minimum number of vertices to cover graph. In this paper, a learning automaton based algorithm is proposed to find minimum vertex cover in graph. In the proposed algorithm, each vertex of graph is equipped with a learning automaton that has two actions in the candidate or noncandidate of the corresponding vertex cover se...

In this paper we present ISA, an approach for learning and exploiting subgoals in episodic reinforcement (RL) tasks. ISA interleaves with the induction of a subgoal automaton, automaton whose edges are labeled by task’s expressed as propositional logic formulas over set high-level events. A also consists two special states: state indicating successful completion task, that task has finished wit...

In this report, we analyze the collective behavior of learning automata which are used in a programming language under development that combines reinforcement learning and symbolic programming [2, 6]. Learning automata can automatically improve their behavior by using a response from a random stationary environment, but when connected with each other, their behavior becomes much complex and har...

Automaton based approaches have enabled robots to perform various complex tasks. However, most existing automaton algorithms highly rely on the manually customized representation of states for considered task, limiting its applicability in deep reinforcement learning algorithms. To address this issue, by incorporating Transformer into learning, we develop a Double-Transformer-guided Temporal Lo...