Learning to Paint With Model-based Deep Reinforcement Learning

被引：74

作者：

Huang, Zhewei ^{[1
,2
]}

Heng, Wen ^{[1
]}

Zhou, Shuchang ^{[1
]}

机构：

[1] Megvii Inc, Beijing, Peoples R China

[2] Peking Univ, Beijing, Peoples R China

来源：

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) | 2019年

关键词：

D O I：

10.1109/ICCV.2019.00880

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We show how to teach machines to paint like human painters, who can use a small number of strokes to create fantastic paintings. By employing a neural renderer in model-based Deep Reinforcement Learning (DRL), our agents learn to determine the position and color of each stroke and make long-term plans to decompose texture-rich images into strokes. Experiments demonstrate that excellent visual effects can be achieved using hundreds of strokes. The training process does not require the experience of human painters or stroke tracking data. The code is available at https://github.com/hzwer/ICCV2019-LearningToPaint.

引用

页码：8708 / 8717

页数：10

共 50 条

[21] A Performance Evaluation of Deep Reinforcement Learning for Model-Based Intrusion Response
Iannucci, Stefano
Barba, Ovidiu Daniel
Cardellini, Valeria
Banicescu, Ioana
[J]. 2019 IEEE 4TH INTERNATIONAL WORKSHOPS ON FOUNDATIONS AND APPLICATIONS OF SELF* SYSTEMS (FAS*W 2019), 2019, : 158 - 163
[22] A Deep Reinforcement Learning Model-Based Optimization Method for Graphic Design
Guo Q.
Wang Z.
[J]. Informatica (Slovenia), 2024, 48 (05): : 121 - 134
[23] Model-Based Deep Learning: On the Intersection of Deep Learning and Optimization
Shlezinger, Nir
Eldar, Yonina C.
Boyd, Stephen P.
[J]. IEEE ACCESS, 2022, 10 : 115384 - 115398
[24] Learning to see via epiretinal implant stimulation in silico with model-based deep reinforcement learning
Lavoie, Jacob
Besrour, Marwan
Lemaire, William
Rouat, Jean
Fontaine, Rejean
Plourde, Eric
[J]. BIOMEDICAL PHYSICS & ENGINEERING EXPRESS, 2024, 10 (02)
[25] Incremental Learning of Planning Actions in Model-Based Reinforcement Learning
Ng, Jun Hao Alvin
Petrick, Ronald P. A.
[J]. PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3195 - 3201
[26] Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning
Huang, Wenzhen
Yin, Qiyue
Zhang, Junge
Huang, Kaiqi
[J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 7848 - 7856
[27] Model gradient: unified model and policy learning in model-based reinforcement learning
Chengxing Jia
Fuxiang Zhang
Tian Xu
Jing-Cheng Pang
Zongzhang Zhang
Yang Yu
[J]. Frontiers of Computer Science, 2024, 18
[28] Model gradient: unified model and policy learning in model-based reinforcement learning
Jia, Chengxing
Zhang, Fuxiang
Xu, Tian
Pang, Jing-Cheng
Zhang, Zongzhang
Yu, Yang
[J]. FRONTIERS OF COMPUTER SCIENCE, 2024, 18 (04)
[29] Model-Based Off-Policy Deep Reinforcement Learning With Model-Embedding
Tan, Xiaoyu
Qu, Chao
Xiong, Junwu
Zhang, James
Qiu, Xihe
Jin, Yaochu
[J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2024, 8 (04): : 2974 - 2986
[30] On Effective Scheduling of Model-based Reinforcement Learning
Lai, Hang
Shen, Jian
Zhang, Weinan
Huang, Yimin
Zhang, Xing
Tang, Ruiming
Yu, Yong
Li, Zhenguo
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34

← 1 2 3 4 5 →