Decentralized Multi-State Q-Learning for NOMA-ALOHA Systems

This paper developed a decentralized multi-state Q-Learning algorithm for joint slot and power level selection in NOMA-ALOHA systems, which models the problem as a Markov Decision Process (MDP) and evaluates the quality of each action by a Q-Table. In a distributed manner, the proposed algorithm aims to find the best action strategy for each user who takes into account both the random collision with other users and the SINR threshold. In particular, novel reward function and state definition are proposed to achieve better exploration and leverage history observations, respectively. Simulation results indicate that the proposed algorithm can improve the average number of users with desired ASR compared to a number of benchmarks.