Noncontingent reinforcement (NCR) consists of delivering a reinforcer on a time-based schedule, independent of responding. Studies evaluating the effectiveness of NCR as treatment for problem behavior have used fixed-time (FT) schedules of reinforcement. In this study, the efficacy of NCR with variable-time (VT) schedules was evaluated by comparing the effects of VT and FT reinforcement schedul...

We propose novel ways of solving Reinforcement Learning tasks (that is, stochastic optimal control tasks) by hybridising Evolutionary Algorithms with methods based on value functions. We call our approach Population-Based Reinforcement Learning. The key idea, from Evolutionary Computation, is that parallel interacting search processes (in this case Reinforcement Learning or Dynamic Programming ...

A finite element model is developed to analyse, as a function of volume fraction, the effects of reinforcement geometry and arrangement within a timber beam. The model is directly validated against experimental equivalents and found to never be mismatched by more than 8% in respect to yield strength predictions. Yield strength increases linearly as a function of increasing reinforcement volume ...

Algorithms for evolutionary computation, which simulate the process of natural selection to solve optimization problems, are an effective tool for discovering high-performing reinforcement-learning policies. Because they can automatically find good representations, handle continuous action spaces, and cope with partial observability, evolutionary reinforcement-learning approaches have a strong ...

This paper discusses why traditional reinforcement learning methods, and algorithms applied to those models, result in poor performance in situated domains characterized by multiple goals, noisy state, and inconsistent reinforcement. We propose a methodology for designing reinforcement functions that take advantage of implicit domain knowledge in order to accelerate learning in such domains. Th...

Many Intelligent Tutoring Systems have been developed using different Artificial Intelligence techniques. In this paper we propose to use Reinforcement Learning for building an intelligent tutoring system to teach autistic students, who can't communicate well with others. In reinforcement learning, a policy is updated for taking appropriate action to teach the student. The main advantage of usi...

Low measles vaccination coverage (VC) leads to recurrent epidemics in many African countries. We describe VC before and after late reinforcement of vaccination activities during a measles epidemic in Niamey, Niger (2003-2004) assessed by Lot Quality Assurance Sampling (LQAS). Neighborhoods of Niamey were grouped into 46 lots based on geographic proximity and population homogeneity. Before reinf...

Feeding behavior in Aplysia can be modified by operant conditioning in which contingent reinforcement is conveyed by the esophageal nerve (E n.). A neuronal analogue of this conditioning in the isolated buccal ganglia was developed by using stimulation of E n. as an analogue of contingent reinforcement. Previous studies indicated that E n. may release dopamine. We used a dopamine antagonist (me...

Error propagation is a common problem in NLP. Reinforcement learning explores erroneous states during training and can therefore be more robust when mistakes are made early in a process. In this paper, we apply reinforcement learning to greedy dependency parsing which is known to suffer from error propagation. Reinforcement learning improves accuracy of both labeled and unlabeled dependencies o...

Chen C. Intelligence moderates reinforcement learning: a minireview of the neural evidence. J Neurophysiol 113: 3459–3461, 2015. First published September 3, 2014; doi:10.1152/jn.00600.2014.—Our understanding of the neural basis of reinforcement learning and intelligence, two key factors contributing to human strivings, has progressed significantly recently. However, the overlap of these two li...