all AI news
Is DQN with experience delay a thing?
I am currently working on my master thesis on Mobile Edge Computing where I follow a paper called "Deep Reinforcement Learning based Computation Offloading and Resource Allocation for MEC" by Ji Li, Hui Gao, Tiejun Lv, and Yueming Lu (published in IEEE in 2018) that proposes a Deep Reinforcement Learning scheme to find optimal resource allocations. The Deep Reinforcement Learning method they use in the paper is called "Deep Q-learning with Experience Delay". However, I cannot understand where they …!-->