当前位置: X-MOL 学术Knowl. Eng. Rev. › 论文详情
Introspective Q-learning and learning from demonstration
The Knowledge Engineering Review ( IF 1.257 ) Pub Date : 2019-01-01 , DOI: 10.1017/s0269888919000031
Mao Li; Tim Brys; Daniel Kudenko

One challenge faced by reinforcement learning (RL) agents is that in many environments the reward signal is sparse, leading to slow improvement of the agent’s performance in early learning episodes. Potential-based reward shaping can help to resolve the aforementioned issue of sparse reward by incorporating an expert’s domain knowledge into the learning through a potential function. Past work on reinforcement learning from demonstration (RLfD) directly mapped (sub-optimal) human expert demonstration to a potential function, which can speed up RL. In this paper we propose an introspective RL agent that significantly further speeds up the learning. An introspective RL agent records its state–action decisions and experience during learning in a priority queue. Good quality decisions, according to a Monte Carlo estimation, will be kept in the queue, while poorer decisions will be rejected. The queue is then used as demonstration to speed up RL via reward shaping. A human expert’s demonstration can be used to initialize the priority queue before the learning process starts. Experimental validation in the 4-dimensional CartPole domain and the 27-dimensional Super Mario AI domain shows that our approach significantly outperforms non-introspective RL and state-of-the-art approaches in RLfD in both domains.
更新日期:2020-03-20

 

全部期刊列表>>
物理学研究前沿热点精选期刊推荐
chemistry
自然职位线上招聘会
欢迎报名注册2020量子在线大会
化学领域亟待解决的问题
材料学研究精选新
GIANT
ACS ES&T Engineering
ACS ES&T Water
ACS Publications填问卷
屿渡论文,编辑服务
阿拉丁试剂right
南昌大学
王辉
南方科技大学
彭小水
隐藏1h前已浏览文章
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
天合科研
x-mol收录
赵延川
李霄羽
廖矿标
朱守非
试剂库存
down
wechat
bug