This paper focuses on a systematic treatment for developing a generic online learning control system based on the fundamental principle of reinforcement learning or more specifically neural dynamic programming. This online learning system improves its performance over time in two aspects: 1) it learns from its own mistakes through the reinforcement signal from the external environment and tries...

Principal aim of a search engine is to provide the sorted results according to user’s requirements. To achieve this aim, it employs ranking methods to rank the web documents based on their significance and relevance to user query. The novelty of this paper is to provide user feedback-based ranking algorithm using reinforcement learning. The proposed algorithm is called RRLUFF, in which the rank...

We propose an artijicial intelligence technique called stochastic learning automata to design an intelligent vehicle path controller. Using the information obtained by on-board sensors and local communication modules, two automata are capable of learning the best possible actions to avoid collisions. Although the learning approach taken is capable of providing a safe decision, optimization of t...

Although several researchers have integrated methods for reinforcement learning (RL) with case-based reasoning (CBR) to model continuous action spaces, existing integrations typically employ discrete approximations of these models. This limits the set of actions that can be modeled, and may lead to non-optimal solutions. We introduce the Continuous Action and State Space Learner (CASSL), an int...

We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent’s explicit representation of all action values to estimate the gradient of the policy, rather than using only the actions that were actually executed. This significantly reduces variance in the gradient updates and removes the n...

Learning Automata (LA) are considered as one of the most powerful tools in the field of reinforcement learning. The family of estimator algorithms is proposed to improve the convergence rate of LA and has made great achievements. However, the estimators perform poorly on estimating the reward probabilities of actions in the initial stage of the learning process of LA. In this situation, a lot o...

The design of reinforcement learning solutions to many problems artificially constrain the action set available to an agent, in order to limit the exploration/sample complexity. While exploring, if an agent can discover new actions that can break through the constraints of its basic/atomic action set, then the quality of the learned decision policy could improve. On the flipside, considering al...

Although several researchers have integrated methods for reinforcement learning (RL) with case-based reasoning (CBR) to model continuous action spaces, existing integrations typically employ discrete approximations of these models. This limits the set of actions that can be modeled, and may lead to non-optimal solutions. We introduce the Continuous Action and State Space Learner (CASSL), an int...

Geographic simulation is concerned with automata-based methodologies for simulating discrete, dynamic, and action-oriented spatial systems, combining cellular automata and multi-agent systems in a spatial context. In this paper, we propose a paradigm for integrating GIS and geosimulation into what we term Geographic Automata Systems (GAS), the latter fusing the two into full-blown, symbiotic sy...

Movements develop in coevolution with regimes and other actors in their environments. Movement trajectories evolve through stochastic processes and are constrained, but not determined, by structures. Coevolution provides a theoretical structure for organizing existing understandings of social movements and sharpening future research. Stochastic thinking is essential for recognizing the both the...