Deep Reinforcement Learning Approach
Deep reinforcement learning (DRL) employs artificial intelligence to enable agents to learn optimal strategies through trial and error within complex environments. Current research focuses on applying DRL algorithms, such as Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), and Actor-Critic methods (including A3C and DDPG), to diverse problems ranging from resource management (energy grids, battery systems) and traffic optimization to financial trading and autonomous systems (robotics, vehicle navigation). The significance of DRL lies in its ability to solve complex decision-making problems beyond the capabilities of traditional methods, leading to improved efficiency, safety, and resource allocation across various sectors.
Papers
Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach
Juan Pinto-Ríos, Felipe Calderón, Ariel Leiva, Gabriel Hermosilla, Alejandra Beghelli, Danilo Bórquez-Paredes, Astrid Lozada, Nicolás Jara, Ricardo Olivares, Gabriel Saavedra
Deep Reinforcement Learning Approach for Trading Automation in The Stock Market
Taylan Kabbani, Ekrem Duman