[review] 자전거 강화학습 - 본문

Reference Controller Learning Method of Self-driving Bicycle Using State-of-the-art Deep Reinforcement Learning Algorithms DeepDeterministicPolicyGradient알고리즘을응용한자전거의자율주행제어 Self-Balancing and Autonomous Driving Control Method for Bicycle using Deep Reinforcement Learning 2. Preliminaries Related works MDP(Markov Decision Process) and Reinforcement Learning 강화학습?

→ 보상 값으로 부터 학습을 하는데 중점 (기계학습의 한 종.....