LEARN EFFECTIVE REPRESENTATION FOR DEEP REINFORCEMENT LEARNING | |
Zhan Yuan1,2; Xu Zhiwei1,2; Fan Guoliang1,2 | |
2022-08 | |
会议日期 | 26 August 2022 |
会议地点 | Taipei, Taiwan |
英文摘要 | 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. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/51924] |
专题 | 融合创新中心_决策指挥与体系智能 |
通讯作者 | Fan Guoliang |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 |
推荐引用方式 GB/T 7714 | Zhan Yuan,Xu Zhiwei,Fan Guoliang. LEARN EFFECTIVE REPRESENTATION FOR DEEP REINFORCEMENT LEARNING[C]. 见:. Taipei, Taiwan. 26 August 2022. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论