Greedy feature replacement for online value function approximation | |
Feng-fei ZHAO ; Zheng QIN ; Zhuo SHAO ; Jun FANG ; Bo-yan REN ; Feng-fei ZHAO ; Zheng QIN ; Zhuo SHAO ; Jun FANG ; Bo-yan REN | |
2016-03-30 ; 2016-03-30 | |
关键词 | Reinforcement learning Function approximation Feature dependency Online expansion Feature replacement TP181 |
其他题名 | Greedy feature replacement for online value function approximation |
中文摘要 | Reinforcement learning(RL) in real-world problems requires function approximations that depend on selecting the appropriate feature representations. Representational expansion techniques can make linear approximators represent value functions more effectively; however, most of these techniques function well only for low dimensional problems. In this paper, we present the greedy feature replacement(GFR), a novel online expansion technique, for value-based RL algorithms that use binary features. Given a simple initial representation, the feature representation is expanded incrementally. New feature dependencies are added automatically to the current representation and conjunctive features are used to replace current features greedily. The virtual temporal difference(TD) error is recorded for each conjunctive feature to judge whether the replacement can improve the approximation. Correctness guarantees and computational complexity analysis are provided for GFR. Experimental results in two domains show that GFR achieves much faster learning and has the capability to handle large-scale problems.; Reinforcement learning(RL) in real-world problems requires function approximations that depend on selecting the appropriate feature representations. Representational expansion techniques can make linear approximators represent value functions more effectively; however, most of these techniques function well only for low dimensional problems. In this paper, we present the greedy feature replacement(GFR), a novel online expansion technique, for value-based RL algorithms that use binary features. Given a simple initial representation, the feature representation is expanded incrementally. New feature dependencies are added automatically to the current representation and conjunctive features are used to replace current features greedily. The virtual temporal difference(TD) error is recorded for each conjunctive feature to judge whether the replacement can improve the approximation. Correctness guarantees and computational complexity analysis are provided for GFR. Experimental results in two domains show that GFR achieves much faster learning and has the capability to handle large-scale problems. |
语种 | 英语 ; 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.lib.tsinghua.edu.cn/ir/item.do?handle=123456789/146795] |
专题 | 清华大学 |
推荐引用方式 GB/T 7714 | Feng-fei ZHAO,Zheng QIN,Zhuo SHAO,et al. Greedy feature replacement for online value function approximation[J],2016, 2016. |
APA | Feng-fei ZHAO.,Zheng QIN.,Zhuo SHAO.,Jun FANG.,Bo-yan REN.,...&Bo-yan REN.(2016).Greedy feature replacement for online value function approximation.. |
MLA | Feng-fei ZHAO,et al."Greedy feature replacement for online value function approximation".(2016). |
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