Reinforcement Learning: A review

强化学习 计算机科学 钢筋 人工智能 心理学 社会心理学
作者
Hanae Moussaoui,Nabil El Akkad,Mohamed Benslimane
出处
期刊:International Journal of Computing and Digital Systems [Deanship of Scientific Research]
卷期号:13 (1): 1465-1483 被引量:11
标识
DOI:10.12785/ijcds/1301118
摘要

Reinforcement learning is considered a sort of machine learning that acquires knowledge of solving problems using the trial-and-error technique.The process starts with the main actor that is the agent interacting with a given environment and attempting to achieve a multi-step goal within this environment.The environment is characterized by a state that the agent detects and examines.On the other hand, due to the agent's several actions, the environment's state changes according to these modifications.Eventually, and at this stage, the agent gets reward signals as it proceeds nearer to its goal.The agent uses these rewards signals to determine which actions were successful and which actions were not.The state action is then repeated and the reward is looped until the agent learns how to operate effectively within the environment using the trial-and-error concept.The agent's main objective is to learn how to always choose the right action given any state of the environment that leads it closer to its goal.In this paper, we gathered all the methods used in the literature.Multi-armed bandits, the Markov decision process, Monte Carlo methods, dynamic programming as well as temporal-difference learning are some of the corresponding methods used to solve reinforcement learning issues.The current paper is organized and structured as follows: we'll start with an introduction followed by a reinforcement learning section where we discussed all the methods and techniques used in the literature.Furthermore, the third section will be about deep reinforcement learning, here we gathered deep reinforcement learning techniques.In the fourth section, we will summarize the reinforcement and deep reinforcement learning algorithms in detail.Furthermore, we will finalize the article with a discussion and a conclusion.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
slz发布了新的文献求助10
刚刚
刚刚
少管我发布了新的文献求助10
刚刚
小透明发布了新的文献求助10
刚刚
1秒前
2秒前
moji完成签到 ,获得积分10
2秒前
香蕉觅云应助淡定的惜采纳,获得10
3秒前
5秒前
微笑芷蕾发布了新的文献求助30
5秒前
5秒前
Shrine发布了新的文献求助10
5秒前
cxy完成签到,获得积分10
6秒前
7秒前
7秒前
田様应助旧梦采纳,获得10
8秒前
mx发布了新的文献求助10
9秒前
寒天抒完成签到 ,获得积分10
10秒前
10秒前
QQ发布了新的文献求助10
11秒前
无情心情完成签到,获得积分10
12秒前
无情心情发布了新的文献求助10
14秒前
老大蒂亚戈应助潇湘雪月采纳,获得10
15秒前
打我呀发布了新的文献求助30
15秒前
16秒前
所所应助科研通管家采纳,获得10
16秒前
汉堡包应助科研通管家采纳,获得10
17秒前
MchemG应助科研通管家采纳,获得10
17秒前
YamDaamCaa应助科研通管家采纳,获得30
17秒前
852应助科研通管家采纳,获得10
17秒前
大模型应助科研通管家采纳,获得30
17秒前
MchemG应助科研通管家采纳,获得10
17秒前
完美世界应助科研通管家采纳,获得30
17秒前
情怀应助科研通管家采纳,获得10
17秒前
科研通AI5应助科研通管家采纳,获得10
17秒前
隐形曼青应助科研通管家采纳,获得10
17秒前
MchemG应助科研通管家采纳,获得10
17秒前
17秒前
李爱国应助深情的雁露采纳,获得10
17秒前
18秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989406
求助须知:如何正确求助?哪些是违规求助? 3531522
关于积分的说明 11254187
捐赠科研通 3270174
什么是DOI,文献DOI怎么找? 1804901
邀请新用户注册赠送积分活动 882105
科研通“疑难数据库(出版商)”最低求助积分说明 809174