A Survey on Simulation Environments for Reinforcement Learning

被引：2

作者：

Kim, Taewoo ^{[1
]}

Jang, Minsu ^{[1
]}

Kim, Jaehong ^{[1
]}

机构：

[1] ETRI, Human Robot Interact Res Sect, Daejeon, South Korea

来源：

2021 18TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS (UR) | 2021年

关键词：

D O I：

10.1109/UR52253.2021.9494694

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Most of the recent studies of reinforcement learning and robotics basically employ computer simulation due to the advantages of time and cost. For this reason, users have to spare time for investigation in order to choose optimal environment for their purposes. This paper presents a survey result that can be a guidance in user's choice for simulation environments. The investigation result includes features, brief historical backgrounds, license policies and formats for robot and object description of the eight most popular environments in robot RL studies. We also propose a quantitative evaluation method for those simulation environments considering the features and a pragmatic point of view.

引用

页码：63 / 67

页数：5

共 50 条

[1] A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments
Padakandla, Sindhu
ACM COMPUTING SURVEYS, 2021, 54 (06)
[2] APPLIED REINFORCEMENT LEARNING FOR DECISION MAKING IN INDUSTRIAL SIMULATION ENVIRONMENTS
Devanga, Ashwin
Badilla, Emily Diaz
Dehghanimohammadabadi, Mohammad
2022 WINTER SIMULATION CONFERENCE (WSC), 2022, : 2819 - 2829
[3] Reinforcement learning: a survey
Kaelbling, Leslie Pack
Littman, Michael L.
Moore, Andrew W.
Journal of Artificial Intelligence Research, 1996, 4 : 237 - 285
[4] ZIPFIAN ENVIRONMENTS FOR REINFORCEMENT LEARNING
Chan, Stephanie C. Y.
Lampinen, Andrew Kyle
Richemond, Pierre
Hill, Felix
CONFERENCE ON LIFELONG LEARNING AGENTS, VOL 199, 2022, 199
[5] Reinforcement learning: A survey
Kaelbling, LP
Littman, ML
Moore, AW
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 1996, 4 : 237 - 285
[6] Reinforcement Learning in Newcomblike Environments
Bell, James
Linsefors, Linda
Oesterheld, Caspar
Skalse, Joar
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[7] Classical Simulation of Quantum Circuits Using Reinforcement Learning: Parallel Environments and Benchmark
Liu, Xiao-Yang
Zhang, Zeliang
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[8] A Survey on Reinforcement Learning and Deep Reinforcement Learning for Recommender Systems
Rezaei, Mehrdad
Tabrizi, Nasseh
DEEP LEARNING THEORY AND APPLICATIONS, DELTA 2023, 2023, 1875 : 385 - 402
[9] Reactive Reinforcement Learning in Asynchronous Environments
Travnik, Jaden B.
Mathewson, Kory W.
Sutton, Richard S.
Pilarski, Patrick M.
FRONTIERS IN ROBOTICS AND AI, 2018, 5
[10] Reinforcement Learning in Configurable Continuous Environments
Metelli, Alberto Maria
Ghelfi, Emanuele
Restelli, Marcello
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97

← 1 2 3 4 5 →