Training Reinforcement Neurocontrollers Using the Polytope Algorithm

A new training algorithm is presented for delayed reinforcement learning problems that does not assume the existence of a critic model and employs the polytope optimization algorithm to adjust the weights of the action network so that a simple direct measure of the training performance is maximized. Experimental results from the application of the method to the pole balancing problem indicate improved training performance compared with critic-based and genetic reinforcement approaches. Key words: reinforcement learning, neurocontrol, optimization, polytope algorithm, pole balancing, genetic reinforcement

• Type: Journal
• Year: 1998
• Where: CORR
• Authors: Aristidis Likas, Isaac E. Lagaris
• Keywords: CORR 1998, Education, Genetic Reinforcement, Polytope Optimization Algorithm, Reinforcement