posts

Recent years, many AI laboratories are working on studying deep reinforcement learning (DRL) which is expected to be a core technology in the future. I am also engaging in DRL research. Here I will write my survey about the Human-level control throught deep reinforcement learning paper. It proposes a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. I will post the most interesting parts of it and also, I will discuss/explain some concepts.