earticle

논문검색

IT Marketing and Policy

Comparison of value-based Reinforcement Learning Algorithms in Cart-Pole Environment

원문정보

Byeong-Chan Han, Ho-Chan Kim, Min-Jae Kang

한국인터넷방송통신학회 International Journal of Internet, Broadcasting and Communication Vol.15 No.3 2023.08 pp.166-175
피인용수 : 0건 (자료제공 : 네이버학술정보)

초록

영어

Reinforcement learning can be applied to a wide variety of problems. However, the fundamental limitation of reinforcement learning is that it is difficult to derive an answer within a given time because the problems in the real world are too complex. Then, with the development of neural network technology, research on deep reinforcement learning that combines deep learning with reinforcement learning is receiving lots of attention. In this paper, two types of neural networks are combined with reinforcement learning and their characteristics were compared and analyzed with existing value-based reinforcement learning algorithms. Two types of neural networks are FNN and CNN, and existing reinforcement learning algorithms are SARSA and Qlearning.

목차

Abstract
1. INTRODUCTION
2. Cart-pole system
3. Value-Based Reinforcement Learning
3.1. Traditional reinforcement learning
3.2. Reinforcement learning with Neural Network
4. EMPIRICAL RESULTS AND OBSERVATION
4.1. RL Reward of cart-pole system
4.2. Pole Oscillation Angle of cart-pole system
5. CONCLUSION
ACKNOWLEDGEMENT
REFERENCES

키워드

저자정보

  • Byeong-Chan Han Graduate student, Dept. of Electronic Engineering, Jeju National University, Korea
  • Ho-Chan Kim Professor, Dept. of Electrical Engineering, Jeju National University, Korea
  • Min-Jae Kang Professor, Dept of Electronic Engineering, Jeju National University, Korea

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 기관로그인 시 무료 이용이 가능합니다.

      • 4,000원

      0개의 논문이 장바구니에 담겼습니다.