Palavra-chave: REINFORCEMENT LEARNING

WORLD MODELS PID CONTROL ACTION SELECTION LOAD ANALYSIS NEURAL NETWORKS CURIOSITY DRIVEN-LEARNING ROBOTICS DEEP REINFORCEMENT LEARNING COGNITIVE ROBOTICS CONTROLE DE ADMISSÃO 5G ARTIFICIAL NEURAL NETWORKS COGNITIVE ARCHITECTURE CMAC COMPUTING CONTINUUM SDN NEURAL CONTROL GENETIC ALGORITHM NESTING PROBLEM ROTEAMENTO REDES SEM FIO COMFORT INTRINSIC MOTIVATION RL MACHINE LEARNING FUZZY CONTROL SELF-DISTRIBUTING SYSTEMS ENERGY-EFFICIENT COMPUTING Q-LEARNING MODULE-BASED LEARNING HEMS