A goal-conditioned policy search method with multi-timescale value function tuning

强化学习 贝尔曼方程 计算机科学 一般化 功能(生物学) 数学优化 价值(数学) 人工智能 约束(计算机辅助设计) 机器人 代表(政治) 机器学习 数学 进化生物学 生物 政治 政治学 数学分析 几何学 法学
作者
Zhihong Jiang,Jiachen Hu,Yan Zhao,Xiao Huang,Hui Li
标识
DOI:10.1108/ria-11-2023-0167
摘要

Purpose Current reinforcement learning (RL) algorithms are facing issues such as low learning efficiency and poor generalization performance, which significantly limit their practical application in real robots. This paper aims to adopt a hybrid model-based and model-free policy search method with multi-timescale value function tuning, aiming to allow robots to learn complex motion planning skills in multi-goal and multi-constraint environments with a few interactions. Design/methodology/approach A goal-conditioned model-based and model-free search method with multi-timescale value function tuning is proposed in this paper. First, the authors construct a multi-goal, multi-constrained policy optimization approach that fuses model-based policy optimization with goal-conditioned, model-free learning. Soft constraints on states and controls are applied to ensure fast and stable policy iteration. Second, an uncertainty-aware multi-timescale value function learning method is proposed, which constructs a multi-timescale value function network and adaptively chooses the value function planning timescales according to the value prediction uncertainty. It implicitly reduces the value representation complexity and improves the generalization performance of the policy. Findings The algorithm enables physical robots to learn generalized skills in real-world environments through a handful of trials. The simulation and experimental results show that the algorithm outperforms other relevant model-based and model-free RL algorithms. Originality/value This paper combines goal-conditioned RL and the model predictive path integral method into a unified model-based policy search framework, which improves the learning efficiency and policy optimality of motor skill learning in multi-goal and multi-constrained environments. An uncertainty-aware multi-timescale value function learning and selection method is proposed to overcome long horizon problems, improve optimal policy resolution and therefore enhance the generalization ability of goal-conditioned RL.
最长约 10秒,即可获得该文献文件

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
王晚意123关注了科研通微信公众号
1秒前
研友_VZG7GZ应助trayheep采纳,获得10
1秒前
小段完成签到,获得积分10
1秒前
1秒前
bkagyin应助wwz采纳,获得10
1秒前
ezekiet完成签到 ,获得积分10
1秒前
2秒前
汉堡包应助kkk采纳,获得10
2秒前
退而求其次完成签到,获得积分10
3秒前
MinQi完成签到,获得积分10
3秒前
毛彬发布了新的文献求助10
3秒前
吴媛媛完成签到 ,获得积分10
3秒前
4秒前
鲤鱼一手发布了新的文献求助10
4秒前
lingjing完成签到,获得积分10
4秒前
华仔应助Tetrahydron采纳,获得30
5秒前
量子星尘发布了新的文献求助10
5秒前
慈祥的冬瓜完成签到,获得积分10
5秒前
5秒前
Mira完成签到,获得积分10
6秒前
温柔手机完成签到,获得积分10
6秒前
6秒前
Lindsay完成签到,获得积分10
7秒前
巧克力完成签到 ,获得积分10
7秒前
7秒前
7秒前
8秒前
8秒前
fengyuenanche完成签到,获得积分10
8秒前
8秒前
9秒前
10秒前
一瓶水发布了新的文献求助10
10秒前
橙子发布了新的文献求助10
10秒前
乐乐发布了新的文献求助20
11秒前
未来发布了新的文献求助10
11秒前
lalafish发布了新的文献求助10
12秒前
oyxz完成签到,获得积分10
12秒前
柔弱小之发布了新的文献求助10
12秒前
13秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
‘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
Aktuelle Entwicklungen in der linguistischen Forschung 300
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 3986829
求助须知:如何正确求助?哪些是违规求助? 3529292
关于积分的说明 11244137
捐赠科研通 3267685
什么是DOI,文献DOI怎么找? 1803843
邀请新用户注册赠送积分活动 881223
科研通“疑难数据库(出版商)”最低求助积分说明 808600