From Animals To Animats 4 Proceedings Of The Fourth International Conference On Simulation Of Adaptive Behavior Complex Adaptive Systems -

rich sutton s publications - abstract policy iteration pi is a recursive process of policy evaluation and improvement to solve an optimal decision making e g reinforcement learning rl or optimal control problem and has served as the fundamental to develop rl methods, recurrent neural networks feedback networks lstm - the human brain is a recurrent neural network rnn a network of neurons with feedback connections it can learn many behaviors sequence processing tasks algorithms programs that are not learnable by traditional machine learning methods, hierarchical control system wikipedia - further reading albus j s 1996 the engineering of mind from animals to animats 4 proceedings of the fourth international conference on simulation of adaptive behavior, deep learning in neural networks an overview sciencedirect - in recent years deep artificial neural networks including recurrent ones have won numerous contests in pattern recognition and machine learning