The thesis assumes these research methods : document investigation method , logical deduction method , generalization method and demonstration method 在研究方法上,本文綜合應(yīng)用了文獻(xiàn)調(diào)查方法、邏輯推理方法、歸納總結(jié)法和實(shí)證法。
Supported by the national natural science foundation of china ( nsfc ) 2 , the research topic of this paper has been focused on reinforcement learning and its applications in mobile robot navigation . one part of the main contents in this paper is the generalization methods for reinforcement learning in solving markov decision problems with continuous states and actions . another part of the main contents is the applications of reinforcement learning methods in the optimization of the path tracking controllers and the autonomous navigation controllers for mobile robots 本文在國(guó)家自然科學(xué)基金項(xiàng)目“增強(qiáng)學(xué)習(xí)泛化方法研究及其在移動(dòng)機(jī)器人導(dǎo)航中的應(yīng)用”的資助下,以增強(qiáng)學(xué)習(xí)及其在移動(dòng)機(jī)器人導(dǎo)航控制中的應(yīng)用為研究?jī)?nèi)容,重點(diǎn)研究了增強(qiáng)學(xué)習(xí)在求解連續(xù)狀態(tài)和行為空間markov決策問題時(shí)的泛化( generalization )方法,并針對(duì)移動(dòng)機(jī)器人在未知環(huán)境中的自主導(dǎo)航和路徑跟蹤控制器的優(yōu)化設(shè)計(jì)問題,研究了增強(qiáng)學(xué)習(xí)在上述領(lǐng)域中的應(yīng)用。