The present work deals with variability, correlation, path-coefficient and selection index for eleven quantitative characters in chickpea. Variability of the studied characters exhibited that they were quantitative in nature and under polygenic control. For all the characters phenotypic variation was greater than those of environmental components of variation. Phenotypic coefficients of variability (PCV) in general were higher than the estimates of genotypic coefficient of variability (GCV) for all the characters, which suggested that the apparent variation is not only due to the genotypes but also due to the influence of environment. The heritability, genetic advance (GA) and genetic advance as percentage of mean (GA %) estimates in the present investigation were found to be low which indicates that the scope for improving traits through selection is limited. SW/P was positively correlated with DMF, NPBMF, NSBMF, PWFD, PdW/P, and NS/P both at phenotypic and genotypic levels. Path coefficient analyses indicated that PdW/P and NS/P having high positive direct effect on yield were the major contributors to SW/P.

This book presents development of efficient reinforcement learning methods in a postgraduate research. A reinforcement learning agent tries every state-action pair to find the optimal policy without prior knowledge about the domain. In large domains visiting every state-action pair is not feasible by an agent, therefore standard reinforcement learning approach is not applicable in solving many real world problems. Three new methods are proposed to make the learning efficient according to the characteristics of the problems: Task-Oriented Reinforcement Learning reduces the problem size by viewing it from the task's viewpoint that clarifies task relevant state variables. Symmetrical-Actions Reinforcement Leaning reduces the size of a learning problem by exploiting partial symmetry over action relevant state variables and representing actions values by a single function. Coordinated Multiagent Reinforcement Learning technique uses coordinator-agent hierarchy to keep the size of individual learning problems small. Depending on problem characteristics all or any of these methods can be applied to solve a problem efficiently using reinforcement learning.