An Artificial Intelligence Approach to Token-Efficient Memory Architecture for Deep Reinforcement Learning via Learned Summarization and DynamicMemory Mechanisms. Indones. J. Cyber-AI Secur. Intell. [Internet]. 2026 Jan. 31 [cited 2026 Oct. 1];1(1):7-17. Available from: https://journal.idnns.org/index.php/ijcasi/article/view/28