Learning to Control an Inverted Pendulum with Connectionist Networks
暂无分享,去创建一个
An inverted pendulum is simulated and cast as a control task with the goal of learning to avoid a subset of states with no a priori knowledge of the pendulum's dynamics. To solve this task a controller must deal with the issues of delayed performance evaluation, learning under uncertainty, and the learning of nonlinear functions. These issues are addressed by connectionist learing procedures that learn to balance the pendulum.
[1] A G Barto,et al. Toward a modern theory of adaptive networks: expectation and prediction. , 1981, Psychological review.
[2] Richard S. Sutton,et al. Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.
[3] Paul E. Utgoff,et al. Learning to control a dynamic physical system , 1987, Comput. Intell..
[4] Charles W. Anderson,et al. Strategy Learning with Multilayer Connectionist Representations , 1987 .