Automated Gait Generation for Simulated Bodies using Deep Reinforcement Learning

被引：0

作者：

Ananthakrishnan, Abhishek ^{[1
]}

Kanakiya, Vatsal ^{[1
]}

Ved, Dipen ^{[1
]}

Sharma, Grishma ^{[1
]}

机构：

[1] KJ Somaiya Coll Engn, Dept Comp Engn, Vidyavihar, Mumbai, India

来源：

PROCEEDINGS OF THE 2018 SECOND INTERNATIONAL CONFERENCE ON INVENTIVE COMMUNICATION AND COMPUTATIONAL TECHNOLOGIES (ICICCT) | 2018年

关键词：

Reinforcement Learning; Reward Function; Value Function; Policy; Action Space; Observation Space; Actor; -; Critic; Policy Gradient; Mujoco; PyTorch;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

A popular problem to solve these days is to propose an algorithm such that a body autonomously learns locomotion. Some of the most efficient and popular contemporary algorithms are Deep Reinforcement Learning algorithms. In this paper, we study three such algorithms from recent times, namely - Deep Deterministic Policy Gradient, Advantage Actor Critic, and Proximal Policy Optimization. We implement and compare the algorithms on the performance metric of average reward per epoch. Given our implementations, we then draw our conclusions on the efficiency of the algorithms proposed and rank the algorithms based on the same.

引用

页码：90 / 95

页数：6

共 50 条

[1] Hierarchical Gait Generation for Modular Robots Using Deep Reinforcement Learning
Wang, Jiayu
Hu, Chuxiong
Zhu, Yu
[J]. 2021 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS (ICM), 2021,
[2] Efficient gait generation using reinforcement learning
Porta, JM
Celaya, E
[J]. CLIMBING AND WALKING ROBOTS, 2001, : 411 - 418
[3] Using Deep Reinforcement Learning for Navigation in Simulated Hallways
Leao, Goncalo
Almeida, Filipe
Trigo, Emanuel
Ferreira, Henrique
Sousa, Armando
Reis, Luis Paulo
[J]. 2023 IEEE INTERNATIONAL CONFERENCE ON AUTONOMOUS ROBOT SYSTEMS AND COMPETITIONS, ICARSC, 2023, : 207 - 213
[4] Automated Vulnerability Exploitation Using Deep Reinforcement Learning
AlMajali, Anas
Al-Abed, Loiy
Ahmad Yousef, Khalil M.
Mohd, Bassam J.
Samamah, Zaid
Abu Shhadeh, Anas
[J]. Applied Sciences (Switzerland), 2024, 14 (20):
[5] Automated Penetration Testing Using Deep Reinforcement Learning
Hu, Zhenguo
Beuran, Razvan
Tan, Yasuo
[J]. 2020 IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (EUROS&PW 2020), 2020, : 2 - 10
[6] Automated Cephalometric Landmark Detection Using Deep Reinforcement Learning
Hong, Woojae
Kim, Seong-Min
Choi, Joongyeon
Ahn, Jaemyung
Paeng, Jun-Young
Kim, Hyunggun
[J]. JOURNAL OF CRANIOFACIAL SURGERY, 2023, 34 (08) : 2336 - 2342
[7] Autonomous Imaging and Mapping of Small Bodies Using Deep Reinforcement Learning
Chan, David M.
Agha-mohammadi, Ali-akbar
[J]. 2019 IEEE AEROSPACE CONFERENCE, 2019,
[8] Overtaking Maneuvers in Simulated Highway Driving using Deep Reinforcement Learning
Kaushik, Meha
Prasad, Vignesh
Krishna, K. Madhava
Ravindran, Balaraman
[J]. 2018 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2018, : 1885 - 1890
[9] Generation of Spacecraft Operations Procedures Using Deep Reinforcement Learning
Harris, Andrew
Valade, Trace
Teil, Thibaud
Schaub, Hanspeter
[J]. JOURNAL OF SPACECRAFT AND ROCKETS, 2022, 59 (02) : 611 - 626
[10] Comprehensive Training and Evaluation on Deep Reinforcement Learning for Automated Driving in Various Simulated Driving Maneuvers
Dong, Yongqi
Datema, Tobias
Wassenaar, Vincent
van de Weg, Joris
Kopar, Cahit Tolga
Suleman, Harim
[J]. 2023 IEEE 26TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, ITSC, 2023, : 6165 - 6170

← 1 2 3 4 5 →