A motor learning model based on the basal ganglia in operant conditioning
Control and Decision Conference（2014）
摘要
In this paper, a motor learning model based on the basal ganglia (BG) in operant conditioning (OC) using actor-critic (AC) learning is presented. The model has three networks for realizing action selecting function of the BS, such as actor network, critic network and explorer network. Actor network uses a probabilistic fuzzy controller for action selection which is enhanced by the introduction of a probability measure into the learning structure based on OC learning. A tropism mechanism is designed for describing intrinsic motivation which is a key factor for animal learning and it can direct the orientation of the agent learning. Critic network is composed of a multi-layer feedforward network and the learning is enhanced by TD(λ) algorithm and gradient descent algorithm. Explorer network is to settle the conflict between exploration and exploitation. Through the experiments of cognitive experiment, the method endows the mobile robot with the capabilities of learning obstacle avoidance and finding the target actively.
更多查看译文
关键词
collision avoidance,fuzzy control,gradient methods,learning systems,mobile robots,motion control,multilayer perceptrons,neurocontrollers,probability,oc learning,action selecting function,action selection,active target finding,actor network,actor-critic learning,agent learning orientation,animal learning,basal ganglia,cognitive experiment,critic network,exploitation,explorer network,gradient descent algorithm,intrinsic motivation,learning enhancement,learning structure,mobile robot,motor learning model,multilayer feedforward network,obstacle avoidance learning,operant conditioning,probabilistic fuzzy controller,probability measure,tropism mechanism,actor-critic,motor learning,reinforcement learning
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要