A Meta-learning System for Automatic Objects Tracking
Qiaolin Li, Wenfeng Wang, Jingjing Zhang · 2022
Recent years, reinforcement learning has been developed in many area and achieve high performance in many application. However, for huge amount data and training will make hard leaning for the agent of reinforcement learning, in the project, the agent of DDQN Network was integrated with LSTM meta learner for learning the game called Cartpole and LunarLander. It get a good performance for large train.