Learn Effective Representation for Deep Reinforcement Learning
Yuan Zhan, Zhiwei Xu, Guoliang Fan · 2022 IEEE International Conference on Multimedia and Expo (ICME) · 2022
Recent years have witnessed an increasing application of deep reinforcement learning (DRL) on video games. While deeper and wider neural networks have played a crucial role in computer vision and natural language processing, such capacity remain under-explored in most DRL works. Under the fact that feature propagation together with large networks contributes to learning a good representation, we propose an end-to-end Large Feature Extractor Network (LFENet) that uses large neural networks with dense connections to train a high-capacity encoder. Even though the increased dimensionality of input is usually thought to result in poor performance for RL agents, we introduce the information bottleneck to alleviate the problem. Finally, we combine LFENet with Proximal Policy Optimization (PPO) algorithm. Through numerical experiments on Atari 2600 video games, we demonstrate our method matches or outperforms state-of-the-art algorithms.