返回
Attentive multi-view reinforcement learning
DOI:10.1007/s13042-020-01130-6.png)
摘要
En 中文
The reinforcement learning process usually takes millions of steps from scratch, due to the limited observation experience. More precisely, the representation approximated by a single deep network is usually limited for reinforcement learning agents. In this paper, we propose a novel multi-view deep attention network (MvDAN), which introduces multi-view representation learning into the reinforcement learning framework for the first time. Based on the multi-view scheme of function approximation, the proposed model approximates multiple view-specific policy or value functions in parallel by estimating the middle-level representation and integrates these functions based on attention mechanisms to generate a comprehensive strategy. Furthermore, we develop the multi-view generalized policy improvement to jointly optimize all policies instead of a single one. Compared with the single-view function approximation scheme in reinforcement learning methods, experimental results on eight Atari benchmarks show that MvDAN outperforms the state-of-the-art methods and has faster convergence and training stability.
Keyword:
Deep reinforcement learning
Function approximation
Multi-view learning
Representation learning
期刊
IF:
2.7
论文数:
3.2K
被引数:
5.6K
机构
引用论文
Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
Fabrication of porous hollow γ-Al2O3 nanofibers by facile electrospinning and its application for water remediation静电纺丝法制备多孔中空 γ-Al2O3纳米纤维及其在水体修复中的应用
Major differences exist in the function and tissue-specific expression of human aflatoxin B1 aldehyde reductase and the principal human aldo-keto reductase AKR1 family members人黄曲霉毒素B1醛还原酶和主要的人醛酮还原酶AKR1家族成员的功能和组织特异性表达存在重大差异
ICT for informal workers in Sub-Saharan Africa: Systematic review and analysis撒哈拉以南非洲非正规工人的信通技术: 系统回顾和分析

